Channel state feedback with dictionary learning

Abstract

In a wireless communication system, a user equipment (UE) may report channel state information (CSI) using a learned dictionary defining a set of sparse vectors. The UE determines a dictionary for learning of CSI reports. For example, the UE receives a shared dictionary from similar and nearby UEs, or the UE trains a learned dictionary based on logged CSI measurements. The UE indicates the learned dictionary to the serving base station. The UE measures CSI for a plurality of channels. The UE reports sparse vectors representing the CSI to the serving base station based on the learned dictionary.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. non-provisional patent application serial number 17 / 817,304, filed on August 3, 2022, entitled “CHANNEL STATE FEEDBACK WITH DICTIONARY LEARNING,” which is expressly incorporated herein by reference in its entirety. Background Art Technical Field

[0003] The present disclosure relates generally to communication systems, and more particularly, to channel state feedback utilizing dictionary learning. Background Art

[0005] Wireless communication systems are widely deployed to provide a variety of telecommunication services, such as telephony, video, data, messaging, and broadcast. Typical wireless communication systems may employ multiple access technologies capable of supporting communication with multiple users by sharing available system resources. Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, and time division synchronous code division multiple access (TD-SCDMA) systems.

[0006] These multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different wireless devices to communicate at a city, country, region, or even global level. An example telecommunication standard is 5G New Radio (NR). 5G NR is part of the continued mobile broadband evolution promulgated by the Third Generation Partnership Project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., with the Internet of Things (IoT)) and other requirements. 5G NR includes services associated with enhanced mobile broadband (eMBB), massive machine type communications (mMTC), and ultra-reliable low latency communications (URLLC). Certain aspects of 5G NR may be based on the 4G Long Term Evolution (LTE) standard. Further improvements to 5G NR technology are needed. In addition, these improvements may also be applicable to other multiple access technologies and telecommunication standards that employ these technologies. Summary of the invention

[0007] The following presents a simplified summary of one or more aspects in order to provide a basic understanding of these aspects. This summary is not an extensive overview of all contemplated aspects, and is neither intended to identify key or important elements of all aspects, nor to describe the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to a more detailed description presented later.

[0008] In some aspects, the technology described herein relates to a method for wireless communications for a user equipment (UE), comprising: determining a learned dictionary for channel state information (CSI) reporting, the learned dictionary defining a set of sparse vectors; indicating the learned dictionary to a serving base station; measuring CSI of multiple channels; and reporting the sparse vector representing the CSI to the serving base station based on the learned dictionary.

[0009]

[0013] In some aspects, the techniques described herein relate to a method in which determining a learned dictionary includes receiving a learned dictionary generated by a similar UE.

[0010] In some aspects, the techniques described herein relate to a method in which a similar UE is a same model as a UE, and the learned dictionary is for locations within a threshold distance of the UE.

[0011]

[0013] In some aspects, the techniques described herein relate to a method in which determining a learned dictionary includes: recording CSI during operation of a UE; and training the learned dictionary based on the recorded CSI.

[0012] In some aspects, the techniques described herein relate to a method in which a dictionary learned based on recorded CSI training includes iterative hard thresholding for sparse principal component analysis (PCA) until a stopping criterion is met.

[0013]

[0013] In some aspects, the techniques described herein relate to a method that also includes receiving a stopping criterion from a serving base station.

[0014]

[0013] In some aspects, the techniques described herein relate to a method in which indicating a learned dictionary to a serving base station includes sharing the learned dictionary with the serving base station.

[0015]

[0013] In some aspects, the techniques described herein relate to a method that also includes sharing a learned dictionary with nearby and similar UEs via a sidelink channel.

[0016] In some aspects, the techniques described herein relate to a method in which reporting a sparse vector includes sending indices and corresponding quantized values ​​of non-zero elements of the sparse vector.

[0017] In some aspects, techniques described herein relate to a method wherein indicating a learned dictionary includes indicating a value of s when a sparse vector is s-sparse.

[0018] In some aspects, the technology described herein relates to a method of wireless communication for a base station, comprising: receiving an indication of a learned dictionary for channel state information (CSI) reporting from a user equipment (UE), the learned dictionary defining a sparse vector; receiving a sparse vector representing CSI measured at the UE from the UE; and determining an estimated channel based on the sparse vector and the learned dictionary of the UE.

[0019]

[0013] In some aspects, the techniques described herein relate to a method that also includes sharing a learned dictionary with similar UEs.

[0020] In some aspects, the techniques described herein relate to a method in which a similar UE is a same model as a UE, and the learned dictionary is for locations within a threshold distance of the UE.

[0021]

[0013] In some aspects, the techniques described herein relate to a method that also includes sending a stopping criterion to a UE for use in iterative hard thresholding to train a learned dictionary.

[0022] In some aspects, the techniques described herein relate to a method in which receiving a sparse vector includes receiving indices of non-zero elements of the sparse vector and corresponding quantized values.

[0023] In some aspects, techniques described herein relate to a method in which receiving an indication of a learned dictionary includes receiving a value of s when the sparse vector is s-sparse.

[0024] In some aspects, the technology described herein relates to an apparatus of a user equipment (UE), comprising: a memory storing computer-executable instructions; at least one processor, the at least one processor coupled to the memory and configured to execute the computer-executable instructions to: determine a learned dictionary for channel state information (CSI) reporting, the learned dictionary defining a set of sparse vectors; indicate the learned dictionary to a serving base station; measure CSI of multiple channels; and report the sparse vector representing the CSI to the serving base station based on the learned dictionary.

[0025]

[0013] In some aspects, the techniques described herein relate to an apparatus wherein, to determine a learned dictionary, at least one processor is configured to receive a learned dictionary generated by a similar UE.

[0026] In some aspects, the techniques described herein relate to an apparatus wherein the similar UEs are of the same model as the UE, and the learned dictionary is for locations within a threshold distance of the UE.

[0027] In some aspects, the techniques described herein relate to an apparatus wherein, to determine a learned dictionary, at least one processor is configured to: record CSI during operation of a UE; and train the learned dictionary based on the recorded CSI.

[0028] In some aspects, the techniques described herein relate to an apparatus wherein, to train a learned dictionary based on recorded CSI, at least one processor is configured to perform iterative hard thresholding for sparse principal component analysis (PCA) until a stopping criterion is met.

[0029] In some aspects, the techniques described herein relate to an apparatus in which at least one processor is configured to receive stopping criteria from a serving base station.

[0030]

[0013] In some aspects, the techniques described herein relate to an apparatus wherein, to indicate the learned dictionary to a serving base station, at least one processor is configured to share the learned dictionary with a serving base station.

[0031]

[0013] In some aspects, the techniques described herein relate to an apparatus in which at least one processor is configured to share a learned dictionary with nearby and similar UEs via a sidelink channel.

[0032] In some aspects, the techniques described herein relate to an apparatus wherein, to report a sparse vector, at least one processor is configured to send indices and corresponding quantized values ​​of non-zero elements of the sparse vector.

[0033] In some aspects, the techniques described herein relate to an apparatus wherein, to indicate a learned dictionary, at least one processor is configured to indicate a value of s when a sparse vector is s-sparse.

[0034] In some aspects, the technology described herein relates to an apparatus for wireless communication of a base station, comprising: a memory storing computer-executable instructions; and at least one processor, the at least one processor coupled to the memory and configured to execute the computer-executable instructions to: receive an indication of a learned dictionary for channel state information (CSI) reporting from a user equipment (UE), the learned dictionary defining a sparse vector; receive from the UE a sparse vector representing CSI measured at the UE; and determine an estimated channel based on the sparse vector and the learned dictionary of the UE.

[0035]

[0013] In some aspects, the techniques described herein relate to an apparatus in which at least one processor is configured to share a learned dictionary with similar UEs.

[0036]

[0013] In some aspects, the techniques described herein relate to an apparatus in which at least one processor is configured to send stopping criteria to a UE for use in iterative hard thresholding to train a learned dictionary.

[0037] In some aspects, the techniques described herein relate to an apparatus wherein, to receive a sparse vector, at least one processor is configured to receive indices of non-zero elements of the sparse vector and corresponding quantized values.

[0038] To achieve the foregoing and related ends, one or more aspects include the features fully described below and particularly pointed out in the claims. The following description and the accompanying drawings set forth in detail some illustrative features of one or more aspects. However, these features are merely indicative of some of the various ways in which the principles of the various aspects may be employed, and this specification is intended to include all such aspects and their equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a diagram illustrating an example of a wireless communication system including an access network in accordance with certain aspects of the present specification.

[0040] Figure 2A is a diagram illustrating an example of a first frame according to certain aspects of the present specification.

[0041] Figure 2B is a diagram illustrating an example of downlink (DL) channels within a subframe in accordance with certain aspects of the present disclosure.

[0042] Figure 2C is a diagram illustrating an example of a second frame according to certain aspects of the present specification.

[0043] Figure 2D is a diagram illustrating an example of uplink (UL) channels within a subframe in accordance with certain aspects of the present disclosure.

[0044] Figure 3 is a diagram illustrating an example of a base station and a user equipment (UE) in an access network in accordance with certain aspects of the present disclosure.

[0045] Figure 4 is a diagram illustrating an example decomposed base station architecture.

[0046] Figure 5 is a diagram of an example autoencoder for channel state information (CSI) feedback.

[0047] Figure 6 is a diagram of an example CSI encoder and decoder using a learned dictionary.

[0048] Figure 7 is a flow chart of an example method for learning a dictionary.

[0049] Figure 8 is a conceptual data flow diagram illustrating the data flow between different means / components in an example UE.

[0050] Fig. 9 is a flow chart of an example method for channel state feedback reporting using a learned dictionary.

[0051] Fig.10 is a conceptual data flow diagram illustrating the data flow between different means / components in an example UE.

[0052] Fig.11 is a flow chart of an example method for channel state feedback reporting using a learned dictionary. DETAILED DESCRIPTION

[0053] The detailed description set forth below in conjunction with the accompanying drawings is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. In order to provide a thorough understanding of the various concepts, the specific embodiments include specific details. However, it is apparent to those skilled in the art that these concepts may be practiced without these specific details. In some instances, well-known structures and components are shown in block diagram form to avoid obscuring these concepts. Although the following description may focus on 5G NR, the concepts described herein may be applicable to other similar fields, such as LTE, LTE-A, CDMA, GSM, and other wireless technologies.

[0054] In wireless communication systems, channel state feedback (CSF) can be used to determine transmission properties. For example, a user equipment (UE) can send channel state information (CSI) to a base station. The base station can use CSI to select downlink transmission properties. CSI can also be used to schedule the UE for uplink transmission.

[0055] Multiple-input multiple-output (MIMO) antenna technology can increase the dimensionality of CSI. For example, the channel between each pair of antennas can vary. Therefore, as the number of antennas used in MIMO increases, the overhead of reporting CSI may also increase. Various techniques have been proposed to reduce CSI overhead, such as codebook-based reporting. However, predefined codebooks can reduce the granularity of CSI information. Another proposal for CSI feedback is to use a machine learning algorithm to compress the CSI at the UE and decompress the CSI at the base station. Such proposals are expected to provide a gain in feedback accuracy relative to the payload size.

[0056] In one aspect, the present disclosure provides a technique for compressing CSI information using dictionary learning. A UE may determine a learned dictionary that defines a set of sparse vectors for CSI reporting. For example, the UE may learn a dictionary based on CSI training recorded at the UE, or the UE may receive a shared dictionary learned at a similar UE. The UE may indicate the learned dictionary to a serving base station. The UE may measure CSI for multiple channels. The UE may report a sparse vector representing CSI to a serving base station based on the learned dictionary.

[0057] In one aspect, because the learned dictionary is specific to the channel conditions for which it is trained, the learned dictionary can provide a gain in feedback accuracy to the payload size. For example, a sparse vector can be efficiently sent by identifying the index of the non-zero elements and the corresponding quantized value. In addition, the training process can be based on a stopping criterion that defines feedback accuracy, and the feedback accuracy can be greater than codebook-based feedback. Although the learned dictionary may involve training at the UE, which imposes a computational burden on the UE, the training can occur while the UE is charging so as not to drain battery power. Additionally, in some implementations, the learned dictionary can be shared between similar UEs so that the training process does not need to be repeated at each UE.

[0058] Several aspects of telecommunication systems will now be presented with reference to various apparatus and methods. These apparatus and methods will be described in the following detailed description and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0059] As an example, an element, or any part of an element, or any combination of elements can be implemented as a "processing system" including one or more processors. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, systems on chip (SoCs), baseband processors, field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gate logic, discrete hardware circuits, and other suitable hardware configured to perform various functionalities described throughout the present disclosure. One or more processors in a processing system can execute software. Whether it is referred to as software, firmware, middleware, microcode, hardware description language, or other names, software should be widely interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, processes, functions, etc.

[0060] Therefore, in one or more example embodiments, the described functions can be implemented with hardware, software, or any combination thereof. If implemented with software, the functions can be stored or decoded on a computer-readable medium as one or more instructions or codes. Computer-readable media include computer storage media. Storage media can be any available media that can be accessed by a computer. Specifically, non-transient computer-readable media do not include transient signals. By way of example and not limitation, such computer-readable media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage devices, magnetic disk storage devices, other magnetic storage devices, combinations of computer-readable media of the above types, or any other medium that can be used to store computer executable code in the form of instructions or data structures that can be accessed by a computer.

[0061] Figure 1 1 is a diagram illustrating an example of a wireless communication system and access network 100. The wireless communication system (also referred to as a wireless wide area network (WWAN)) includes a base station 102, a UE 104, an evolved packet core (EPC) 160, and another core network (e.g., a 5G core (5GC) 190). The base station 102 may include a macro cell (a high-power cellular base station) and / or a small cell (a low-power cellular base station). A macro cell includes a base station. A small cell includes a femto cell, a pico cell, and a micro cell.

[0062] One or more of the UEs 104 may include a channel state feedback component 140 that utilizes a learned dictionary to send CSI information as a sparse vector. The channel state feedback component 140 may include a learning component 142 that is configured to determine a learned dictionary for CSI reporting. The learned dictionary defines a set of sparse vectors. The channel state feedback component 140 may include a dictionary component 144 that is configured to send the learned dictionary to a serving base station. The channel state feedback component 140 may include a measurement component 146 that is configured to measure CSI for multiple channels. The channel state feedback component 140 may include a reporting component 148 that is configured to report a sparse vector representing CSI to a serving base station based on the learned dictionary.

[0063] In one aspect, one or more of the base stations 102 may include a feedback receiving component 120 that utilizes a learned dictionary to receive a sparse vector indicating CSI information. For example, the feedback receiving component 120 may include a dictionary receiving component 122 that is configured to receive a learned dictionary for channel state information (CSI) reporting from a user equipment (UE). The learned dictionary may define a sparse vector. The feedback receiving component 120 may include a vector receiving component 122 that is configured to receive a sparse vector representing CSI measured at the UE from the UE. The feedback receiving component 120 may include a decoding component 126 that is configured to determine an estimated channel based on the sparse vector and the learned dictionary of the UE.

[0064] A base station 102 configured for 4G LTE (collectively referred to as the Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (E-UTRAN)) can be connected to the EPC 160 interface via a backhaul link 132 (e.g., an S1 interface). The backhaul link 132 can be wired or wireless. A base station 102 configured for 5G NR (collectively referred to as the Next Generation RAN (NG-RAN)) can be connected to the 5GC 190 via a backhaul link 184. The backhaul link 184 can be wired or wireless. Among other functions, the base station 102 can perform one or more of the following functions: delivery of user data, radio channel encryption and decryption, integrity protection, header compression, mobility control functions (e.g., handover, dual connectivity), inter-cell interference coordination, connection establishment and release, load balancing, distribution of non-access stratum (NAS) messages, NAS node selection, synchronization, radio access network (RAN) sharing, multimedia broadcast multicast service (MBMS), subscriber and equipment tracking, RAN information management (RIM), paging, positioning, and delivery of warning messages. The base stations 102 may communicate with each other directly or indirectly (e.g., through the EPC 160 or the 5GC 190) over a backhaul link 134 (e.g., an X2 interface). The backhaul link 134 may be wired or wireless.

[0065] Base station 102 can communicate wirelessly with UE 104. Each of base stations 102 can provide communication coverage for a corresponding geographic coverage area 110. There may be overlapping geographic coverage areas 110. For example, a small cell 102' may have a coverage area 110' that overlaps with the coverage area 110 of one or more macro base stations 102. A network including both small cells and macro cells can be referred to as a heterogeneous network. A heterogeneous network can also include a home evolved Node B (eNB) (HeNB), which can provide services to a restricted group called a closed subscriber group (CSG). The communication link 112 between base station 102 and UE 104 may include an uplink (UL) (also called a reverse link) transmission from UE 104 to base station 102 and / or a downlink (DL) (also called a forward link) transmission from base station 102 to UE 104. The communication link 112 can use multiple input multiple output (MIMO) antenna technology, including spatial multiplexing, beamforming and / or transmit diversity. The communication link can be through one or more carriers. For each carrier allocated in the carrier aggregation for a total of up to Yx MHz (x component carriers) for transmission in each direction, the base station 102 / UE 104 can use a spectrum of up to Y MHz (e.g., 5 MHz, 10 MHz, 15 MHz, 20 MHz, 100 MHz, 400 MHz, etc.) bandwidth. The carriers may or may not be adjacent to each other. The allocation of carriers may be asymmetric with respect to DL and UL (e.g., more or fewer carriers may be allocated for DL ​​compared to UL). The component carrier may include a primary component carrier and one or more secondary component carriers. The primary component carrier may be referred to as a primary cell (PCell) and the secondary component carrier may be referred to as a secondary cell (SCell).

[0066] Some UEs 104 may communicate with each other using a device-to-device (D2D) communication link 158. The D2D communication link 158 may use DL / UL WWAN spectrum. The D2D communication link 158 may use one or more sidelink channels, such as a physical sidelink broadcast channel (PSBCH), a physical sidelink discovery channel (PSDCH), a physical sidelink shared channel (PSSCH), a physical sidelink control channel (PSCCH), and a physical sidelink feedback channel (PSFCH). The D2D communication may be through various wireless D2D communication systems, such as, for example, FlashLinQ, WiMedia, Bluetooth, ZigBee, Wi-Fi based on IEEE 802.11 standards, LTE, or NR.

[0067] The wireless communication system may also include a Wi-Fi access point (AP) 150 that communicates with a Wi-Fi station (STA) 152 via a communication link 154 in the 5 GHz unlicensed spectrum. When communicating in the unlicensed spectrum, the STA 152 / AP 150 may perform a clear channel assessment (CCA) to determine whether the channel is available prior to communication.

[0068] The small cell 102' may operate in licensed and / or unlicensed spectrum. When operating in the unlicensed spectrum, the small cell 102' may employ NR and use the same 5 GHz unlicensed spectrum used by the Wi-Fi AP 150. The small cell 102' employing NR in the unlicensed spectrum may improve the coverage of the access network and / or increase the capacity of the access network.

[0069] Base station 102 (whether a small cell 102' or a large cell (e.g., a macro base station)) may include an eNB, a gNodeB (gNB), or other types of base stations. Some base stations (such as gNB 180) may operate in one or more frequency bands within the electromagnetic spectrum.

[0070] The electromagnetic spectrum is often subdivided into various categories, bands, channels, etc. based on frequency / wavelength. In 5G NR, two initial operating bands have been identified as frequency range designations FR1 (410MHz–7.125GHz) and FR2 (24.25GHz–52.6GHz). Frequencies between FR1 and FR2 are often referred to as mid-band frequencies. Although a portion of FR1 is greater than 6GHz, FR1 is often (interchangeably) referred to as the “sub-6GHz” band in various documents and articles. A similar naming issue sometimes occurs with FR2, which is often (interchangeably) referred to as the “millimeter wave” band in various documents and articles, although it is different from the extremely high frequency (EHF) band (30GHz to 300GHz) identified as the “millimeter wave” (mmW) band by the International Telecommunication Union (ITU).

[0071] In view of the above aspects, unless otherwise specifically stated, it should be understood that if the term "below 6 GHz" or the like is used herein, it can be broadly referred to as a frequency that can be less than 6 GHz, can be within FR1, or can include mid-band frequencies. In addition, unless otherwise specifically stated, it should be understood that if the term "millimeter wave" or the like is used herein, it can be broadly referred to as a frequency that can include mid-band frequencies, can be within FR2, or can be within the EHF band. Communications using mmW radio frequency bands have extremely high path loss and short range. The mmW base station 180 can utilize beamforming 182 with the UE 104 to compensate for this path loss and short range.

[0072] Base station 180 may transmit beamformed signals to UE 104 on one or more transmit beams 182'. UE 104 may receive beamformed signals from base station 180 on one or more receive beams 182". UE 104 may also transmit beamformed signals to base station 180 in one or more transmit directions. Base station 180 may receive beamformed signals from UE 104 in one or more receive directions. Base station 180 / UE 104 may perform beam training to determine the best receive direction and transmit direction for each of base station 180 / UE 104. The transmit direction and receive direction for base station 180 may be the same or different. The transmit direction and receive direction for UE 104 may be the same or different. In the case of a synchronous network, cells from base station 180 may generally be aligned. Different receive beams 182" may provide the best performance for each cell. The UE may perform neighbor cell search and beam measurement to identify the best receive beam 182" for each cell.

[0073] The EPC 160 may include a mobility management entity (MME) 162, other MMEs 164, a serving gateway 166, a multimedia broadcast multicast service (MBMS) gateway 168, a broadcast multicast service center (BM-SC) 170, and a packet data network (PDN) gateway 172. The MME 162 may communicate with a home subscriber server (HSS) 174. The MME 162 is a control node that handles signaling between the UE 104 and the EPC 160. In general, the MME 162 provides bearer and connection management. All user Internet Protocol (IP) packets are passed through the serving gateway 166, which itself is connected to the PDN gateway 172. The PDN gateway 172 provides UE IP address allocation and other functions. The PDN gateway 172 and the BM-SC 170 are connected to IP services 176. The IP services 176 may include the Internet, an intranet, an IP multimedia subsystem (IMS), PS streaming services, and / or other IP services. The BM-SC 170 may provide functionality for MBMS user service configuration and delivery. The BM-SC 170 may serve as an entry point for content provider MBMS delivery, may be used to authorize and initiate MBMS bearer services in a public land mobile network (PLMN), and may be used to schedule MBMS delivery. The MBMS gateway 168 may be used to distribute MBMS services to base stations 102 belonging to a multicast broadcast single frequency network (MBSFN) area that broadcasts a specific service, and may be responsible for session management (start / stop) and for collecting eMBMS-related billing information.

[0074] 5GC 190 may include an access and mobility management function (AMF) 192, other AMFs 193, a session management function (SMF) 194, and a user plane function (UPF) 195. AMF 192 may communicate with unified data management (UDM) 196. AMF 192 is a control node that handles signaling between UE 104 and 5GC 190. Generally speaking, AMF 192 provides QoS flow and session management. All user Internet Protocol (IP) packets are passed through UPF 195. UPF 195 provides UE IP address allocation and other functions. UPF 195 is connected to IP service 197. IP service 197 may include the Internet, intranet, IP multimedia subsystem (IMS), PS streaming service and / or other IP services.

[0075] A base station may also be referred to as a gNB, a Node B, an evolved Node B (eNB), an access point, a base transceiver, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), a transmit receive point (TRP), or some other suitable term. Base station 102 provides an access point to EPC 160 or 5GC 190 for UE 104. Examples of UE 104 include a cellular phone, a smart phone, a Session Initiation Protocol (SIP) phone, a laptop, a personal digital assistant (PDA), a satellite radio, a global positioning system, a multimedia device, a video device, a digital audio player (e.g., an MP3 player), a camera, a game console, a tablet device, a smart device, a wearable device, a vehicle, an electric meter, a gas pump, a large or small kitchen appliance, a healthcare device, an implant, a sensor / actuator, a display, or any other similarly functional device. Some of UE 104 may be referred to as IoT devices (e.g., a parking meter, a gas pump, a toaster, a vehicle, a heart monitor, etc.). UE 104 may also be referred to as a station, a mobile station, a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communication device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a user agent, a mobile client, a client, or some other suitable terminology.

[0076] FIG. 2A to FIG. 2D is a resource diagram illustrating an example frame structure and channels that may be used for uplink transmissions, downlink transmissions, and sidelink transmissions to UE 104 including channel state feedback 140. Figure 2A FIG200 is a diagram illustrating an example of a first subframe within a 5G NR frame structure. Figure 2B is a diagram 230 illustrating an example of DL channels within a 5G NR subframe. Figure 2CFIG250 is a diagram illustrating an example of a second subframe within a 5G NR frame structure. Figure 2D FIG280 is a diagram illustrating an example of UL channels within a 5G NR subframe. The 5G NR frame structure may be FDD, where for a particular set of subcarriers (carrier system bandwidth), subframes within that subcarrier set are dedicated to either DL or UL, or may be TDD, where for a particular set of subcarriers (carrier system bandwidth), subframes within that subcarrier set are dedicated to both DL and UL. Figure 2A , Figure 2C In the example provided, the 5G NR frame structure is assumed to be TDD, where subframe 4 is configured with slot format 28 (most of which are DL), where D is DL, U is UL, and X can be used flexibly between DL / UL, and subframe 3 is configured with slot format 34 (most of which are UL). Although subframes 3 and 4 are shown as having slot formats 34 and 28, respectively, any particular subframe can be configured to have any of the various available slot formats 0 to 61. Slot formats 0 and 1 are DL and UL, respectively. Other slot formats 2 to 61 include a mix of DL, UL and flexible symbols. The UE is configured with the slot format through the received slot format indicator (SFI) (dynamically configured through DL control information (DCI) or semi-statically / statically configured through radio resource control (RRC) signaling). Note that the following description also applies to the 5G NR frame structure as TDD.

[0077] Other wireless communication technologies may have different frame structures and / or different channels. A frame (10ms) may be divided into 10 subframes of equal size (1ms). Each subframe may include one or more time slots. A subframe may also include a microslot, which may include 7, 4 or 2 symbols. Each time slot may contain 7 or 14 symbols, depending on the time slot configuration. For time slot configuration 0, each time slot may include 14 symbols, and for time slot configuration 1, each time slot may include 7 symbols. The symbol on the DL may be a cyclic prefix (CP) OFDM (CP-OFDM) symbol. The symbol on the UL may be a CP-OFDM symbol (for high throughput scenarios) or a discrete Fourier transform (DFT) spread OFDM (DFT-s-OFDM) symbol (also known as a single carrier frequency division multiple access (SC-FDMA) symbol) (for power-limited scenarios; limited to single-stream transmission). The number of time slots in a subframe is based on the time slot configuration and parameter set. For slot configuration 0, different parameter sets μ0 to 5 allow 1, 2, 4, 8, 16, and 32 slots per subframe, respectively. For slot configuration 1, different parameter sets 0 to 2 allow 2, 4, and 8 slots per subframe, respectively. Thus, for slot configuration 0 and parameter set μ, there are 14 symbols per slot and 2 per subframe. μtime slots. The subcarrier spacing and symbol length / duration are functions of the parameter set. The subcarrier spacing can be equal to 2 μ *15kHz, where μ is parameter set 0 to 5. Therefore, the subcarrier spacing for parameter set μ=0 is 15kHz, and the subcarrier spacing for parameter set μ=5 is 480kHz. The symbol length / duration is inversely related to the subcarrier spacing. FIG. 2A to FIG. 2D An example is provided for slot configuration 0 with 14 symbols per slot and parameter set μ=0 with 1 slot per subframe. The subcarrier spacing is 15 kHz and the symbol duration is about 66.7 μs.

[0078] A resource grid may be used to represent a frame structure. Each slot includes a resource block (RB) (also referred to as a physical RB (PRB)) extending over 12 consecutive subcarriers. The resource grid is divided into a plurality of resource elements (REs). The number of bits carried by each RE depends on the modulation scheme.

[0079] like Figure 2A As illustrated, some of the REs carry reference (pilot) signals (RS) for the UE. The RS may include a demodulation RS (DMRS) 202 (indicated as Rx for a particular configuration, where 100x is the port number, but other DMRS configurations are possible) and a channel state information reference signal (CSI-RS) for channel estimation at the UE. The RS may also include a beam measurement RS (BRS), a beam refinement RS (BRRS), and a phase tracking RS (PT-RS).

[0080] Figure 2BExamples of various DL channels within a subframe of a frame are illustrated. A physical downlink control channel (PDCCH) carries DCI within one or more control channel elements (CCEs), each CCE including nine RE groups (REGs), each REG including four consecutive REs in an OFDM symbol. A primary synchronization signal (PSS) may be within symbol 2 (e.g., PSS symbol 242) of a particular subframe of a frame. The PSS is used by UE 104 to determine subframe / symbol timing and physical layer identity. A secondary synchronization signal (SSS) may be within symbol 4 (e.g., SSS symbol 246) of a particular subframe of a frame. The SSS is used by the UE to determine the physical layer cell identification group number and radio frame timing. Based on the physical layer identification and the physical layer cell identification group number, the UE may determine a physical cell identifier (PCI). Based on the PCI, the UE may determine the location of the aforementioned DMRS 202. A physical broadcast channel (PBCH) carrying a master information block (MIB) may be logically grouped with the PSS and SSS to form a synchronization signal (SS) / PBCH block, also referred to as an SSB 232. The PBCH may be sent on symbols 3 to 5 of a subframe, where symbols 3 and 5 are referred to as PBCH symbols 244, 248, for example, because these symbols primarily include RBs for the PBCH. The DMRS 202 may be interleaved with RBs for the PBCH (e.g., every four RBs) to allow the PBCH to be decoded. The MIB provides the number of RBs in the system bandwidth and the system frame number (SFN). The physical downlink shared channel (PDSCH) carries user data, broadcast system information not sent over the PBCH (such as a system information block (SIB)), and paging messages.

[0081] As in Figure 2C As illustrated in FIG, some REs carry DMRS for channel estimation at the base station (indicated as R for one particular configuration, but other DMRS configurations are possible). The UE may send DMRS for the physical uplink control channel (PUCCH) and DMRS for the physical uplink shared channel (PUSCH). The PUSCH DMRS may be sent in the first or first two symbols of the PUSCH. The PUCCH DMRS may be sent in different configurations depending on whether a short PUCCH or a long PUCCH is sent and depending on the specific PUCCH format used. Although not shown, the UE may send a sounding reference signal (SRS). The SRS may be used by the base station for channel quality estimation to enable frequency-dependent scheduling of the UL.

[0082] Figure 2DExamples of various UL channels within a subframe of a frame are illustrated. The PUCCH may be located at a position as indicated in one configuration. The PUCCH carries uplink control information (UCI), such as scheduling requests, channel quality indicators (CQI), precoding matrix indicators (PMI), rank indicators (RI), and HARQ ACK / NACK feedback. The PUSCH carries data and may additionally be used to carry buffer status reports (BSRs), power headroom reports (PHRs), and / or UCI.

[0083] Figure 3 3 is a block diagram of a base station 310 in an access network communicating with a UE 350. In the DL, IP packets from the EPC 160 may be provided to the controller / processor 375. The controller / processor 375 implements layer 3 and layer 2 functionality. Layer 3 includes a radio resource control (RRC) layer, and layer 2 includes a service data adaptation protocol (SDAP) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, and a medium access control (MAC) layer. The controller / processor 375 provides RRC layer functionality associated with broadcasting of system information (e.g., MIB, SIB), RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), inter-radio access technology (RAT) mobility, and measurement configuration for UE measurement reporting; PDCP layer functionality associated with header compression / decompression, security (encryption, decryption, integrity protection, integrity verification), and handover support functions; RLC layer functionality associated with delivery of upper layer packet data units (PDUs), error correction through ARQ, concatenation, segmentation and reassembly of RLC service data units (SDUs), re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto transport blocks (TBs), demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0084] The transmit (Tx) processor 316 and the receive (Rx) processor 370 implement layer 1 functionality associated with various signal processing functions. Layer 1 (which includes the physical (PHY) layer) may include error detection on the transmission channel, forward error correction (FEC) decoding / decoding of the transmission channel, interleaving, rate matching, mapping to the physical channel, modulation / demodulation of the physical channel, and MIMO antenna processing. The Tx processor 316 handles the mapping to the signal constellation diagram based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-phase shift keying (M-PSK), M-quadrature amplitude modulation (M-QAM)). The decoded and modulated symbols can then be split into parallel streams. Subsequently, each stream can be mapped to an OFDM subcarrier, multiplexed with a reference signal (e.g., a pilot) in the time domain and / or frequency domain, and then combined using an inverse fast Fourier transform (IFFT) to produce a physical channel carrying a time domain OFDM symbol stream. The OFDM stream is spatially pre-decoded to produce multiple spatial streams. Channel estimates from a channel estimator 374 may be used to determine the coding and modulation schemes, as well as for spatial processing. Channel estimates may be derived based on reference signals and / or channel condition feedback sent by the UE 350. Each spatial stream may then be provided to a different antenna 320 via a separate transmitter 318Tx. Each transmitter 318Tx may modulate an RF carrier with a corresponding spatial stream for transmission.

[0085] At the UE 350, each receiver 354Rx receives a signal through its corresponding antenna 352. Each receiver 354Rx recovers the information modulated onto the RF carrier and provides the information to a receive (Rx) processor 356. The Tx processor 368 and the Rx processor 356 implement layer 1 functionality associated with various signal processing functions. The Rx processor 356 can perform spatial processing on the information to recover any spatial stream destined for the UE 350. If multiple spatial streams are destined for the UE 350, they can be combined into a single OFDM symbol stream by the Rx processor 356. The Rx processor 356 then converts the OFDM symbol stream from the time domain to the frequency domain using a fast Fourier transform (FFT). The frequency domain signal includes a separate OFDM symbol stream for each subcarrier of the OFDM signal. The symbols on each subcarrier and the reference signal are recovered and demodulated by determining the signal constellation point most likely to be sent by the base station 310. These soft decisions can be based on the channel estimate calculated by the channel estimator 358. The soft decisions are then decoded and deinterleaved to recover the data and control signals originally sent on the physical channel by the base station 310. The data and control signals are then provided to the controller / processor 359, which implements layer 3 and layer 2 functionality.

[0086] The controller / processor 359 may be associated with a memory 360 that stores program codes and data. The memory 360 may be referred to as a computer-readable medium. In the UL, the controller / processor 359 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover IP packets from the EPC 160 or 5GC 190. The controller / processor 359 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0087] Similar to the functionality described in conjunction with DL transmissions performed by the base station 310, the controller / processor 359 provides RRC layer functionality associated with system information (e.g., MIB, SIB) acquisition, RRC connection, and measurement reporting; PDCP layer functionality associated with header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); RLC layer functionality associated with delivery of upper layer PDUs, error correction through ARQ, concatenation, segmentation and reassembly of RLC SDUs, resegmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto TBs, demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0088] Channel estimates derived by the channel estimator 358 from a reference signal or feedback sent by the base station 310 may be used by the Tx processor 368 to select appropriate coding and modulation schemes, and to facilitate spatial processing. The spatial streams generated by the Tx processor 368 may be provided to different antennas 352 via separate transmitters 354Tx. Each transmitter 354Tx may modulate an RF carrier with a corresponding spatial stream for transmission.

[0089] UL transmissions are processed at the base station 310 in a manner similar to that described in conjunction with the receiver functionality at the UE 350. Each receiver 318Rx receives a signal through its corresponding antenna 320. Each receiver 318Rx recovers information modulated onto an RF carrier and provides the information to an Rx processor 370.

[0090] The controller / processor 375 may be associated with a memory 376 that stores program codes and data. The memory 376 may be referred to as a computer readable medium. In the UL, the controller / processor 375 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, control signal processing to recover IP packets from the UE 350. The IP packets from the controller / processor 375 may be provided to the EPC 160. The controller / processor 375 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0091] At least one of the Tx processor 368, the Rx processor 356, and the controller / processor 359 may be configured to perform Figure 1 The channel state feedback component 140 combines various aspects.

[0092] At least one of the Tx processor 316, the Rx processor 370, and the controller / processor 375 may be configured to perform Figure 1 The feedback receiving component 120 combines various aspects.

[0093] Figure 4 A diagram illustrating an example decomposed base station 400 architecture is shown. The decomposed base station 400 framework may include one or more central units (CUs) 410 that may communicate directly with a core network 420 via a backhaul link, or indirectly with the core network 420 through one or more decomposed base station units, such as a near real-time (near-RT) RAN intelligent controller (RIC) 425 via an E2 link, or a non-real-time (non-RT) RIC 415 associated with a service management and orchestration (SMO) framework 405, or both. The CU 410 may communicate with one or more distributed units (DUs) 430 via respective midhaul links, such as an F1 interface. The DU 430 may communicate with one or more radio units (RUs) 440 via respective fronthaul links. The RU 440 may communicate with respective UEs 104 via one or more radio frequency (RF) access links. In some implementations, a UE 104 may be served simultaneously by multiple RUs 440.

[0094] Each of these units (i.e., CU 410, DU 430, RU 440, and near-RT RIC 425, non-RT RIC 415, and SMO framework 405) may include or be coupled to one or more interfaces configured to receive or send signals, data, or information (collectively referred to as signals) via a wired transmission medium or a wireless transmission medium. Each of the units or an associated processor or controller that provides instructions to the communication interface of these units may be configured to communicate with one or more of the other units via a transmission medium. For example, these units may include a wired interface configured to receive or send signals to one or more of the other units via a wired transmission medium. Additionally, these units may include a wireless interface that may include a receiver, a transmitter, or a transceiver (such as a radio frequency (RF) transceiver) configured to receive or send signals, or both, to one or more of the other units on a wireless transmission medium.

[0095] In some aspects, CU 410 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), etc. Each control function may be implemented using an interface that is configured to communicate signals with other control functions hosted by CU 410. CU 410 may be configured to handle user plane functionality (i.e., central unit-user plane (CU-UP)), control plane functionality (i.e., central unit-control plane (CU-CP)), or a combination thereof. In some specific implementations, CU 410 may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP unit may communicate bidirectionally with the CU-CP unit via an interface (such as an E1 interface). As needed, CU 410 may be implemented to communicate with DU 430 for network control and signaling.

[0096] DU 430 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RUs 440. In some aspects, DU 430 may host one or more of a radio link control (RLC) layer, a medium access control (MAC) layer, and one or more high physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc.) at least in part according to a functional split such as those defined by the 3rd Generation Partnership Project (3GPP). In some aspects, DU 430 may also host one or more low PHY layers. Each layer (or module) may be implemented using an interface that is configured to communicate signals with other layers (and modules) hosted by DU 430 or with control functions hosted by CU 410.

[0097] Lower layer functionality may be implemented by one or more RUs 440. In some deployments, a RU 440 controlled by a DU 430 may correspond to a logical node that hosts RF processing functions or low PHY layer functions (such as performing Fast Fourier Transform (FFT), Inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc.), or both, based at least in part on a functional split (such as a lower layer functional split). In such an architecture, the RU 440 may be implemented to handle over-the-air (OTA) communications with one or more UEs 104. In some implementations, real-time and non-real-time aspects of control plane and user plane communications with the RU 440 may be controlled by the corresponding DU 430. In some scenarios, such a configuration may enable the DU 430 and the CU 410 to be implemented in a cloud-based RAN architecture (such as a vRAN architecture).

[0098] The SMO framework 405 may be configured to support RAN deployment and provisioning of non-virtualized network elements and virtualized network elements. For non-virtualized network elements, the SMO framework 405 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (such as an O1 interface). For virtualized network elements, the SMO framework 405 may be configured to interact with a cloud computing platform (such as an open cloud (O-Cloud) 490) to perform network element lifecycle management (such as instantiating virtualized network elements) via a cloud computing platform interface (such as an O2 interface). Such virtualized network elements may include, but are not limited to, CU 410, DU 430, RU 440, and near-RT RIC 425. In some specific implementations, the SMO framework 405 may communicate with hardware aspects of the 4G RAN (such as an open eNB (O-eNB) 411) via the O1 interface. Additionally, in some specific implementations, the SMO framework 405 may communicate directly with one or more RUs 440 via the O1 interface. The SMO framework 405 may also include a non-RT RIC 415 configured to support the functionality of the SMO framework 405 .

[0099] The non-RT RIC 415 may be configured to include logic functions that enable non-real-time control and optimization of RAN elements and resources, artificial intelligence / machine learning (AI / ML) workflows including model training and updating, or policy-based guidance of applications / features in the near-RT RIC 425. The non-RT RIC 415 may be coupled to or in communication with the near-RT RIC 425 (such as via an A1 interface). The near-RT RIC 425 may be configured to include logic functions that enable near-real-time control and optimization of RAN elements and resources via data collection and actions through an interface (such as via an E2 interface) that connects one or more CUs 410, one or more DUs 430, or both, and the O-eNB with the near-RT RIC 425.

[0100] In some implementations, in order to generate an AI / ML model to be deployed in the near-RT RIC 425, the non-RT RIC 415 may receive parameters or external enrichment information from an external server. Such information may be utilized by the near-RT RIC 425 and may be received from a non-network data source or from a network function at the SMO framework 405 or the non-RT RIC 415. In some examples, the non-RT RIC 415 or the near-RT RIC 425 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 415 may monitor long-term trends and patterns in performance and employ AI / ML models to perform corrective actions through the SMO framework 405 (such as via reconfiguration of O1) or via creation of RAN management policies (such as A1 policies).

[0101] Figure 5 is a diagram of an example autoencoder 500 for CSI feedback. The autoencoder 500 may include an encoder network 502 at the UE 104 and a decoder network 504 at the UE 102. The encoder network 502 and the decoder network 504 are jointly trained but deployed separately. For example, the encoder network 502 and the decoder network 504 may be implemented in the UE 104 and the base station 102, respectively, or vice versa. The autoencoder 500 is an unsupervised learning algorithm in which the encoder network 502 attempts to produce a lower dimensional representation z of the input X, and the decoder network 504 attempts to reconstruct the input X from z. For example, the encoder network 502 may be a first neural network including an input layer 510 that receives the input X, one or more hidden layers 520, and a bottleneck layer 530. The bottleneck layer 530 may have a smaller dimension than the input layer X. For example, the input layer X may include a channel estimate for each pair of receive antennas and transmit antennas (possibly for multiple subbands), and the bottleneck layer or representation z may be a one-dimensional vector. The decoder network 504 may also be a neural network. The decoder network 504 may include a bottleneck layer as an input layer 530 , one or more hidden layers 540 , and an output layer 550 .

[0102] Proposals for ML model-based CSI feedback have focused on autoencoders such as autoencoder 500. Autoencoders can outperform traditional methods such as compressive sensing in some scenarios (e.g., low compression rates). Autoencoders attempt to learn a compressive representation from training data, so they attempt to tailor the compression for that specific type of data. One problem with using autoencoders is the complexity of the signaling framework through which Tx and Rx can interact for ML module updates, parameter exchange, and / or joint training.

[0103] Figure 66 is a diagram 600 of an example CSI encoder 610 and decoder 630 using a learned dictionary 624. The learned dictionary 624 can be applicable to a single base station 102 and one or more UEs 104. The encoder 610 can select the learned dictionary 624. In some implementations, the encoder 610 can receive the learned dictionary 624 from another UE 104, for example, via a sidelink communication.

[0104] In some implementations, the encoder 610 can train the learned dictionary 624 based on the measured CSI. For example, during the training phase, the encoder 610 and / or the measurement component 146 can measure the CSI of multiple channels. The encoder 610 can store the measured CSI in a CSI log 622. For example, the CSI log 622 can store the CSI with associated side information, such as the cell, geographic location, and time of day when the CSI was measured. The geographic location can be an area within a cell. As described below with respect to Figure 7 As discussed in further detail, the encoder 610 and / or the learning component 144 may train the learned dictionary 624, for example, using iterative hard thresholding. The encoder 610 and / or the dictionary component 144 may send the learned dictionary 624 to the base station 102. For example, the learned dictionary 624 (e.g., the new dictionary 628) may be sent as an RRC information element or a MAC-CE. During the inference phase, the encoder 610 may perform an encoding operation 626 on the CSI 620 measured by the measurement component 146. For example, encoding the CSI may include applying the CSI to the learned dictionary (e.g., via a matrix operation including a matrix multiplication) to determine a sparse vector 640. The encoder 610 and / or the reporting component 148 may send the sparse vector 640 to the base station 102. For example, the sparse vector 640 may be sent as uplink control information (UCI) on a PUCCH or a PUSCH. The sparse vector 640 may be efficiently sent by identifying the index and quantization value of the non-zero element. In some implementations, a first non-zero element can be identified by an index, and subsequent non-zero elements can be identified based on differences from previous non-zero elements.

[0105] The decoder 630 may receive the new dictionary 628 and store the new dictionary 628 in a set of UE dictionaries 632. In some implementations, the UE dictionary 632 may associate an identifier with each dictionary and track the active dictionary for each UE. For example, when the UE changes its geographic location defined by a region (e.g., indoors and outdoors), the UE may switch between dictionaries. The UE dictionary 632 may provide the current dictionary to a decoding operation 634. The decoding operation 634 may receive a sparse vector 640. The decoding operation 634 may decode the sparse vector by applying the sparse vector to the current dictionary of the UE. For example, the decoding operation 634 may include multiplying the learned dictionary with the sparse vector to reconstruct the CSI information. The decoding operation 634 may output a CSI 636 including a channel estimate for each of the plurality of channels.

[0106] Figure 7 is a flow chart of an example method 700 for learning a dictionary. The method 700 can be performed by the learning component 142 to train the learned dictionary 624. In general, the method 700 can utilize an iterative hard thresholding method.

[0107] At block 710, method 700 may include receiving an input H, where H is a data set matrix of samples (eg, samples of channel estimation). That is, The goal of the dictionary learning method 700 is to learn a dictionary D with k atoms. Make And z i is sparse. The general problem can be to minimize the absolute value of the difference between H and DZ under constraints. That is:

[0108] In some implementations, the constraint D T D=I can be replaced by another suitable condition, such as ‖D‖ F =1.

[0109] At block 720, Z0 may be randomly initialized. The general problem may then be solved using iterative hard thresholding for principal component analysis. At block 730, the learning component 142 may update D by solving the following problem, which may be referred to as an orthogonal Prucker problem.

[0110]

[0111] The orthogonal Prucker problem can be solved with a closed-form solution using univariate decomposition.

[0112] At block 740, the learning component 142 may be based on Update Z. The learning component 142 can solve

[0113] At block 750 , the learning component 142 can use iterative hard thresholding on Z . Blocks 730, 740, and 750 may be repeated until a stopping criterion is met. For example, the stopping criterion may be that the mean square error difference between the training set and the validation set is less than a threshold. In some implementations, the stopping criterion (e.g., a threshold) may be configured by the base station 102.

[0114] At block 760 , the learning component 142 may output the dictionary D as the learned dictionary 624 .

[0115] Figure 8 8 is a conceptual data flow diagram 800 illustrating the data flow between different means / components in an example UE 804, which may be an example of UE 104 and includes a channel state feedback component 140. Figure 1 As discussed, channel state feedback component 140 may include a learning component 142 , a dictionary component 144 , a measurement component 146 , and a reporting component 148 .

[0116] UE 104 may also include a receiver component 870 and a transmitter component 872. Receiver component 870 may include, for example, an RF receiver for receiving the signals described herein. Transmitter component 872 may include, for example, an RF transmitter for transmitting the signals described herein. In some implementations, receiver component 870 and transmitter component 872 may be co-located on a transceiver (such as Figure 3 in Tx / Rx 354).

[0117] Receiver component 870 can receive a downlink signal, such as a reference signal (eg, CSI-RS). Receiver component 870 can provide the reference signal to measurement component 146.

[0118] The measuring component 146 can receive the CSI-RS from the receiver component 870. The measuring component 146 can be configured to measure the CSI based on the CSI-RS. For example, the measuring component 146 can calculate a channel estimate for each antenna pair of a transmit antenna at the base station 102 and a receive antenna at the UE 104. In some implementations, the measuring component 146 can calculate a channel quality indicator (CQI) for each pair of a transmit antenna at the base station 102 and a receive antenna at the UE 104. The measuring component 146 can provide the CSI to the learning component 142 and / or the reporting component 148.

[0119] The learning component 142 can receive the CSI from the measurement component 146. The learning component 142 can store the CSI in the CSI log 622. In some implementations, the learning component 142 can determine a training set based on a subset of the CSI in the CSI log 622. For example, the training set can include CSI measurements within a geographic area or within a period of time (e.g., time of day). The learning component 142 can use the method 700 ( Figure 7 ) Train the learned dictionary based on the input of the training set (e.g., H). The learning component 142 can provide the learned dictionary to the dictionary component 144.

[0120] The dictionary component 144 may receive a learned dictionary from the learning component 142. In some implementations, the dictionary component 144 may receive a transferred dictionary from another UE or base station. The dictionary component 144 may be configured to select a current dictionary. For example, the dictionary component 144 may select the nearest dictionary for a geographic area or a time of day. When a new learned dictionary is selected, the dictionary component 144 may send the learned dictionary to the base station 102 via the transmitter component 872. In some implementations, the dictionary component 144 may share the learned dictionary with nearby and similar UEs via a side link channel (e.g., by transmitting side link communications via the transmitter component 872). For example, nearby UEs may be within a geographic distance so that the RF channels may be similar, and similar UEs may be UEs of the same model or have the same antenna configuration. The dictionary component 144 may configure the reporting component 148 with a current dictionary (e.g., the learned dictionary 624).

[0121] Report component 148 can receive a configuration of a current dictionary from dictionary component 144. Report component 148 can receive CSI measurements from measurement component 146. Report component 148 can encode CSI using learned dictionary 624. For example, report component 148 can calculate a sparse vector Z based on the CSI and D. Report component 148 can send the sparse vector Z by identifying the index of the non-zero elements and the corresponding quantized value.

[0122] Fig. 9 9 is a flow chart of an example method 900 for a UE to perform CSI reporting using a learned dictionary. The method 900 may be performed by a UE, such as a UE 104, which may include a memory 360 and may be the entire UE 104 or a component of the UE 104, such as a channel state feedback component 140, a Tx processor 368, an Rx processor 356, or a controller / processor 359. The method 900 may be performed by a channel state feedback component 140 in communication with a feedback receiving component 120 of one or more base stations 102. Optional blocks are shown with dashed lines.

[0123] At block 910, method 900 includes determining a learned dictionary for CSI reporting, the learned dictionary defining a set of sparse vectors. In some implementations, for example, UE 104, Rx processor 356, or controller / processor 359 may execute channel state feedback component 140 or learning component 142 to determine a learned dictionary for CSI reporting, the learned dictionary defining a set of sparse vectors. In some implementations, at subblock 912, for example, block 910 may optionally include receiving a learned dictionary generated by a similar UE. For example, the similar UE may be the same model as UE 104, and the learned dictionary may be for locations within a threshold distance of UE 104. In some implementations, at subblock 914, block 910 may optionally include recording CSI during operation of the UE. In such an implementation, at subblock 916, block 910 may include training the learned dictionary based on the recorded CSI. Training the learned dictionary may include the above-described Figure 7 Method 700 discussed. In some implementations, subblock 916 may include receiving a stopping criterion from a serving base station at subblock 917. At subblock 918, subblock 916 may include iterative hard thresholding for sparse PCA until the stopping criterion is met. Thus, the UE 104, Rx processor 356, or controller / processor 359 performing channel state feedback 140 or learning component 142 may provide means for determining a learned dictionary for CSI reporting, the learned dictionary defining a set of sparse vectors.

[0124] At block 920, method 900 includes indicating the learned dictionary to the serving base station. In some implementations, for example, UE 104, TX processor 368, or controller / processor 359 may execute channel state feedback component 140 or dictionary component 144 to indicate the learned dictionary to the serving base station. In some implementations, at subblock 922, block 920 may include sharing the learned dictionary with the serving base station. In some implementations, at subblock 924, block 920 may include indicating the value of s when the sparse vector is s-sparse. Thus, UE 104, TX processor 368, or controller / processor 359 executing channel state feedback 140 or dictionary component 144 may provide a means for indicating the learned dictionary to the serving base station.

[0125] At block 930, the method 900 may optionally include sharing the learned dictionary with nearby and similar UEs via a side link channel. In some implementations, for example, the UE 104, the TX processor 368, or the controller / processor 359 may execute the channel state feedback component 140 or the dictionary component 144 to share the learned dictionary with nearby and similar UEs via a side link channel. Thus, the UE 104, the TX processor 368, or the controller / processor 359 executing the channel state feedback 140 or the dictionary component 144 may provide a means for sharing the learned dictionary with nearby and similar UEs via a side link channel.

[0126] At block 940, the method 900 includes measuring CSI of the plurality of channels. In some implementations, for example, the UE 104, the Rx processor 356, or the controller / processor 359 may execute the channel state feedback component 140 or the measurement component 146 to measure the CSI of the plurality of channels. Thus, the UE 104, the Rx processor 356, or the controller / processor 359 executing the channel state feedback 140 or the measurement component 146 may provide a means for measuring the CSI of the plurality of channels.

[0127] At block 950, method 900 includes reporting a sparse vector representing CSI to a serving base station based on the learned dictionary. In some implementations, for example, UE 104, TX processor 368, or controller / processor 359 may execute channel state feedback component 140 or reporting component 148 to report a sparse vector representing CSI to a serving base station based on the learned dictionary. In some implementations, for example, at subblock 952, block 950 may include sending indices of non-zero elements of the sparse vector and corresponding quantized values. Thus, UE 104, TX processor 368, or controller / processor 359 performing channel state feedback 140 or dictionary component 144 may provide a means for reporting a sparse vector representing CSI to a serving base station based on the learned dictionary.

[0128] Fig.10 is a conceptual data flow diagram 1000 illustrating the data flow between different means / components in an example base station 1002, which may be an example of base station 102 and includes feedback receiving component 120. Figure 1 As discussed, the feedback receiving component 120 may include a dictionary receiving component 122 , a vector receiving component 124 , and a decoding component 126 .

[0129] Base station 1002 may also include a receiver component 1070 and a transmitter component 1072. Receiver component 1070 may include, for example, an RF receiver for receiving the signals described herein. Transmitter component 1072 may include, for example, an RF transmitter for transmitting the signals described herein. In some implementations, receiver component 1070 and transmitter component 1072 may be co-located on a transceiver (such as Figure 3 In Tx / Rx318).

[0130] Receiver component 1070 can receive uplink signals such as an indication of a dictionary and a sparse vector indicating CSI. Receiver component 1070 can provide the indication of the dictionary to dictionary receiving component 122. Receiver component 1070 can provide the sparse vector to vector receiving component 124.

[0131] Dictionary receiving component 122 can receive an indication of a dictionary from receiver component 1070. In some implementations, the indication of the dictionary is a copy of the dictionary. For example, dictionary receiving component 122 can receive an RRC message or MAC-CE that includes the dictionary. In some implementations, the indication of the dictionary can be an identification of a dictionary that has been previously provided to base station 102. For example, the indication can identify a dictionary generated by a similar UE. Dictionary receiving component 122 can store the dictionary and / or the association between UE 104 and the dictionary in UE dictionary 632. Dictionary receiving component 122 can configure decoding component 126 using the current dictionary of UE 104.

[0132] The vector receiving component 124 can receive the sparse vector via the receiver component 1070. For example, the sparse vector can be received as uplink control information (UCI) received on the PUCCH or PUSCH. In some implementations, the vector is indicated as an index of non-zero elements and corresponding quantized values, and the vector receiving component 124 can generate a vector including all elements (including zero values). The vector receiving component 124 can provide the sparse vector to the decoding component 126.

[0133] The decoding component 126 can receive the current dictionary from the dictionary receiving component 122. The decoding component 126 can receive the sparse vector from the vector receiving component 124. The decoding component 126 can be configured to decode the sparse vector based on the current dictionary of the UE 104. For example, the decoding component 126 can multiply each quantized value of the sparse matrix (z) by the corresponding atom (d) from the codebook and add the resulting vectors to determine H.

[0134] In some implementations, base station 1002 can optionally include configuration component 1020. Configuration component can send various configuration information to UE 104 via transmitter component 1072. For example, configuration component 1020 can share a learned dictionary (e.g., from UE 104) with similar UEs. As another example, configuration component 1020 can send stopping criteria to UE 104 for use in iterative hard thresholding to train the learned dictionary.

[0135] Fig.11 1 is a flow chart of an example method 1100 for a base station to receive CSI reports using a learned dictionary. The method 1100 may be performed by a base station, such as base station 102, which may include memory 376 and may be the entire base station 102 or a component of base station 102, such as feedback receiving component 120, Tx processor 316, Rx processor 370, or controller / processor 375. The method 1100 may be performed by feedback receiving component 120 in communication with feedback receiving component 120 of one or more base stations 102. Optional blocks are shown with dashed lines.

[0136] At block 1110, the method 1100 may optionally include sending a stopping criterion to the UE for use in iterative hard thresholding to train the learned dictionary. In some implementations, for example, the base station 102, the Tx processor 316, or the controller / processor 375 may execute the feedback receiving component 120 or the configuration component 1020 to send a stopping criterion to the UE for use in iterative hard thresholding to train the learned dictionary. Thus, the base station 102, the Tx processor 316, or the controller / processor 375 processor executing the feedback receiving component 120 or the configuration component 1020 may provide a means for sending a stopping criterion to the UE for use in iterative hard thresholding to train the learned dictionary.

[0137] At block 1120, the method 1100 includes receiving an indication of a learned dictionary for CSI reporting from a UE, the learned dictionary defining a sparse vector. In some implementations, for example, the base station 102, the Rx processor 370, or the controller / processor 375 may execute the feedback receiving component 120 or the dictionary receiving component 122 to receive an indication of a learned dictionary 624 for CSI reporting from the UE 104, the learned dictionary 624 defining a sparse vector. In some implementations, at sub-block 1122, the block 1120 may optionally include receiving a value of s when the sparse vector is s-sparse. The value of s may indicate the number of non-zero elements in the sparse vector. Thus, the base station 102, the Rx processor 370, or the controller / processor 375 executing the feedback receiving component 120 or the configuration component 1020 may provide a means for receiving an indication of a learned dictionary for CSI reporting from a UE, the learned dictionary defining a sparse vector.

[0138] At block 1130, the method 1100 includes receiving, from the UE, a sparse vector representing CSI measured at the UE. In some implementations, for example, the base station 102, the Rx processor 370, or the controller / processor 375 may execute the feedback receiving component 120 or the vector receiving component 124 to receive, from the UE 104, the sparse vector 640 representing the CSI 620 measured at the UE. For example, in some implementations, at subblock 1132, the block 1130 may include receiving indices of non-zero elements of the sparse vector and corresponding quantized values. Thus, the base station 102, the Rx processor 370, or the controller / processor 375 executing the feedback receiving component 120 or the vector receiving component 124 may provide a means for receiving, from the UE, a sparse vector representing CSI measured at the UE.

[0139] At block 1140, the method 1100 can optionally include sharing the learned dictionary with similar UEs. In some implementations, for example, the base station 102, the Tx processor 316, or the controller / processor 375 can execute the feedback receiving component 120 or the configuration component 1020 to share the learned dictionary with similar UEs. Thus, the base station 102, the Tx processor 316, the Rx processor 370, or the controller / processor 375 executing the feedback receiving component 120 or the configuration component 1020 can provide a means for sharing the learned dictionary with similar UEs.

[0140] At block 1150, the method 1100 includes determining an estimated channel based on the sparse vector and the UE's learned dictionary. In some implementations, for example, the base station 102, the Rx processor 370, or the controller / processor 375 may execute the feedback receiving component 120 or the decoding component 126 to determine the estimated channel based on the sparse vector 640 and the UE's learned dictionary 624. Thus, the base station 102, the Tx processor 316, the Rx processor 370, or the controller / processor 375 executing the feedback receiving component 120 or the decoding component 126 may provide a means for determining an estimated channel based on the sparse vector and the UE's learned dictionary.

[0141] The following numbered clauses provide an overview of various aspects of the disclosure:

[0142] 1. A method for wireless communication of a user equipment (UE), the method comprising:

[0143] determining a learned dictionary for channel state information (CSI) reporting, the learned dictionary defining a set of sparse vectors;

[0144] indicating the learned dictionary to a serving base station;

[0145] measuring CSI of multiple channels; and

[0146] A sparse vector representing the CSI is reported to the serving base station based on the learned dictionary.

[0147] 2. The method of clause 1, wherein determining the learned dictionary comprises receiving a learned dictionary generated by a similar UE.

[0148] 3. The method of clause 2, wherein the similar UEs are of the same model as the UE, and the learned dictionary is for locations within a threshold distance of the UE.

[0149] 4. A method according to any one of clauses 1 to 3, wherein determining the learned dictionary comprises:

[0150] logging CSI during operation of the UE; and

[0151] The learned dictionary is trained based on the recorded CSI.

[0152] 5. The method of clause 4, wherein training the learned dictionary based on the recorded CSI comprises iterative hard thresholding for sparse principal component analysis (PCA) until a stopping criterion is met.

[0153] 6. The method of clause 5, further comprising receiving the stopping criteria from the serving base station.

[0154] 7. A method according to any of clauses 4 to 6, wherein indicating the learned dictionary to the serving base station comprises sharing the learned dictionary with the serving base station.

[0155] 8. A method as described in any of clauses 4 to 7, further comprising sharing the learned dictionary with nearby and similar UEs via a sidelink channel.

[0156] 9. A method according to any of clauses 1 to 8, wherein reporting the sparse vector comprises sending indices and corresponding quantized values ​​of non-zero elements of the sparse vector.

[0157] 10. A method according to any one of clauses 1 to 9, wherein indicating the learned dictionary comprises indicating a value of s when the sparse vector is s-sparse.

[0158] 11. A device of a user equipment (UE), the device comprising:

[0159] a memory storing computer-executable instructions; and

[0160] At least one processor coupled to the memory and configured to execute the computer-executable instructions to perform the method according to any of clauses 1 to 10.

[0161] 12. An apparatus of a user equipment (UE), the apparatus comprising means for performing a method according to any of clauses 1 to 10.

[0162] 13. A non-transitory computer-readable medium storing computer-executable instructions which, when executed by a processor of a user equipment (UE), cause the UE to perform the method of any of clauses 1 to 10.

[0163] 14. A wireless communication method for a base station, the method comprising:

[0164] receiving, from a user equipment (UE), an indication of a learned dictionary for channel state information (CSI) reporting, the learned dictionary defining a sparse vector;

[0165] receiving, from the UE, a sparse vector representing CSI measured at the UE; and

[0166] An estimated channel is determined based on the sparse vector and the learned dictionary of the UE.

[0167] 15. The method of clause 14, further comprising sharing the learned dictionary with similar UEs.

[0168] 16. The method of clause 15, wherein the similar UEs are of the same model as the UE, and the learned dictionary is for locations within a threshold distance of the UE.

[0169] 17. A method as described in any of clauses 14 to 16, further comprising sending a stopping criterion to the UE for use in iterative hard thresholding in training the learned dictionary.

[0170] 18. The method of any of clauses 14 to 17, wherein receiving a sparse vector comprises receiving indices and corresponding quantized values ​​of non-zero elements of the sparse vector.

[0171] 19. A method according to any of clauses 14 to 18, wherein receiving the indication of the learned dictionary comprises receiving a value of s when the sparse vector is s-sparse.

[0172] 20. An apparatus for wireless communication of a base station, the apparatus comprising:

[0173] a memory storing computer-executable instructions; and

[0174] At least one processor coupled to the memory and configured to execute the computer-executable instructions to perform the method according to any of clauses 14 to 19.

[0175] 21. An apparatus of a base station, the apparatus comprising means for performing the method according to any of clauses 14 to 19.

[0176] 22. A non-transitory computer-readable medium storing computer-executable instructions which, when executed by a processor of a base station, cause the base station to perform the method of any of clauses 14 to 19.

[0177] The preceding description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. Therefore, the claims are not intended to be limited to the aspects shown herein, but to conform to the full scope consistent with the language claims, wherein the elements mentioned in the singular are not intended to mean "one and only one", unless specifically so stated, but "one or more". The word "exemplary" is used herein to mean "used as an example, instance, or illustration". Any aspect described herein as "exemplary" is not necessarily interpreted as being preferred or having an advantage over other aspects. Unless otherwise specifically stated, the term "some" refers to one or more. Combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B, and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof", include any combination of A, B, and / or C, and may include multiple A, multiple B, or multiple C. Specifically, combinations such as "at least one of A, B, or C," "one or more of A, B, or C," "at least one of A, B, and C," "one or more of A, B, and C," and "A, B, C, or any combination thereof" may be A only, B only, C only, A and B, A and C, B and C, or A and B and C, wherein any such combination may include one or more members of A, B, or C. All structural and functional equivalents of the elements throughout the various aspects described in this disclosure that are known or will later be known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be covered by the claims. In addition, regardless of whether such disclosure is explicitly recited in the claims, anything disclosed herein is not intended to be disclosed to the public. Words such as "module," "mechanism," "element," "device," etc. cannot replace the word "component." Therefore, no claim element will be interpreted as a functional component unless the element is explicitly recorded using the phrase "component for..."

Claims

1. A method for wireless communication of a user equipment (UE), the method comprising: determining a learned dictionary for channel state information (CSI) reporting, the learned dictionary defining a set of sparse vectors; indicating the learned dictionary to a serving base station; Measure CSI of multiple channels; as well as A sparse vector representing the CSI is reported to the serving base station based on the learned dictionary. 2 . The method of claim 1 , wherein determining the learned dictionary comprises receiving a learned dictionary generated by a similar UE.

3. The method of claim 2, wherein the similar UE is of the same model as the UE, and the learned dictionary is for locations within a threshold distance of the UE.

4. The method of claim 1 , wherein determining the learned dictionary comprises: recording CSI during operation of the UE; as well as The learned dictionary is trained based on the recorded CSI.

5. The method of claim 4, wherein training the learned dictionary based on the recorded CSI comprises iterative hard thresholding for sparse principal component analysis (PCA) until a stopping criterion is met. The method of claim 5 , further comprising receiving the stopping criteria from the serving base station.

7. The method of claim 4, wherein indicating the learned dictionary to the serving base station comprises sharing the learned dictionary with the serving base station.

8. The method of claim 4, further comprising sharing the learned dictionary with nearby and similar UEs via a sidelink channel.

9. The method of claim 1, wherein reporting the sparse vector comprises sending indices and corresponding quantized values ​​of non-zero elements of the sparse vector.

10. The method of claim 1, wherein indicating the learned dictionary comprises indicating a value of s when the sparse vector is s-sparse.

11. A wireless communication method for a base station, the method comprising: receiving, from a user equipment (UE), an indication of a learned dictionary for channel state information (CSI) reporting, the learned dictionary defining a sparse vector; receiving, from the UE, a sparse vector representing CSI measured at the UE; as well as An estimated channel is determined based on the sparse vector and the learned dictionary of the UE.

12. The method of claim 11, further comprising sharing the learned dictionary with similar UEs.

13. The method of claim 12, wherein the similar UE is of the same model as the UE, and the learned dictionary is for locations within a threshold distance of the UE.

14. The method of claim 11, further comprising sending a stopping criterion to the UE for use in iterative hard thresholding to train the learned dictionary.

15. The method of claim 11, wherein receiving the sparse vector comprises receiving indices of non-zero elements of the sparse vector and corresponding quantized values.

16. The method of claim 11, wherein receiving the indication of the learned dictionary comprises receiving a value of s when the sparse vector is s-sparse.

17. A device of a user equipment (UE), the device comprising: a memory storing computer executable instructions; and at least one processor coupled to the memory and configured to execute the computer-executable instructions to: determining a learned dictionary for channel state information (CSI) reporting, the learned dictionary defining a set of sparse vectors; indicating the learned dictionary to a serving base station; Measure CSI of multiple channels; as well as A sparse vector representing the CSI is reported to the serving base station based on the learned dictionary.

18. The apparatus of claim 17, wherein to determine the learned dictionary, the at least one processor is configured to receive a learned dictionary generated by a similar UE.

19. The apparatus of claim 18, wherein the similar UE is of the same model as the UE, and the learned dictionary is for locations within a threshold distance of the UE.

20. The apparatus of claim 17, wherein to determine the learned dictionary, the at least one processor is configured to: logging CSI during operation of the UE; and The learned dictionary is trained based on the recorded CSI.

21. The apparatus of claim 20, wherein to train the learned dictionary based on the recorded CSI, the at least one processor is configured to perform iterative hard thresholding for sparse principal component analysis (PCA) until a stopping criterion is met.

22. The apparatus of claim 21, wherein the at least one processor is configured to receive the stopping criteria from the serving base station.

23. The apparatus of claim 21, wherein to indicate the learned dictionary to the serving base station, the at least one processor is configured to share the learned dictionary with the serving base station.

24. The apparatus of claim 21, wherein the at least one processor is configured to share the learned dictionary with nearby and similar UEs via a sidelink channel.

25. The apparatus of claim 17, wherein to report the sparse vector, the at least one processor is configured to send indices and corresponding quantized values ​​of non-zero elements of the sparse vector.

26. The apparatus of claim 17, wherein to indicate the learned dictionary, the at least one processor is configured to indicate a value of s when a sparse vector is s-sparse.

27. An apparatus for wireless communication of a base station, the apparatus comprising: a memory storing computer executable instructions; and at least one processor coupled to the memory and configured to execute the computer-executable instructions to: receiving, from a user equipment (UE), an indication of a learned dictionary for channel state information (CSI) reporting, the learned dictionary defining a sparse vector; receiving, from the UE, a sparse vector representing CSI measured at the UE; as well as An estimated channel is determined based on the sparse vector and the learned dictionary of the UE.

28. The apparatus of claim 27, wherein the at least one processor is configured to share the learned dictionary with similar UEs.

29. The apparatus of claim 27, wherein the at least one processor is configured to send a stopping criterion to the UE for use in iterative hard thresholding in training the learned dictionary.

30. The apparatus of claim 27, wherein to receive the sparse vector, the at least one processor is configured to receive indices of non-zero elements of the sparse vector and corresponding quantized values.

Images