Unlock instant, AI-driven research and patent intelligence for your innovation.

Model optimization method and device in secret sharing state and storage medium

A technology of secret sharing and optimization methods, applied in the field of secure computing, which can solve the problems of unfavorable machine learning models such as fast iterative training and slow processing speed, and achieve the effect of fast model optimization operation and improved computing speed

Pending Publication Date: 2022-02-18
ALIBABA GRP HLDG LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the processing speed of the root calculation operation in the secure multi-party computing protocol is slow, so it is not conducive to the rapid iterative training of the machine learning model

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Model optimization method and device in secret sharing state and storage medium
  • Model optimization method and device in secret sharing state and storage medium
  • Model optimization method and device in secret sharing state and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and corresponding drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0014] Gradient descent optimizer is an iterative method in machine learning training, which is used to adaptively adjust the parameters of machine learning models. In the field of machine learning, commonly used gradient descent optimizers include ordinary stochastic gradient descent optimizers, such as SGD (Batch Gradient Descen, batch gradient desc...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the invention provides a model optimization method and device in a secret sharing state and a storage medium. In the model optimization method in the secret sharing state, when a machine learning model is optimized in the secret sharing state, model parameters adopted by last iteration of machine learning are used as input parameters of an adaptive gradient descent optimizer. In the adaptive gradient descent optimizer, polynomial calculation is adopted to replace root number calculation, so that root number calculation in a secret sharing state is avoided, the calculation speed of gradient descent is improved, and model optimization operation can be quickly realized based on the adaptive gradient descent optimizer in secure multi-party calculation.

Description

technical field [0001] The present application relates to the technical field of secure computing, and in particular to a model optimization method, device and storage medium under a secret sharing state. Background technique [0002] In the iterative training process of machine learning, the adaptive gradient descent optimizer (adaptive gradient descent optimizer) is often used to update the model parameters. Adaptive gradient descent optimizers have the advantage of faster iterations and more stability. The operator of the adaptive gradient descent optimizer includes the operation of calculating the root sign. [0003] In the prior art, there is a method for training a machine learning model using a secure multi-party computing protocol. Secure multi-party computing is a computing protocol in which multiple participants provide input and jointly calculate output. However, the processing speed of the root sign calculation operation in the secure multi-party computing pro...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N20/00
CPCG06N20/00
Inventor 陆文杰黄智聪洪澄
Owner ALIBABA GRP HLDG LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com