Method and device for optimizing hyperparameters in machine learning model

Abstract

An embodiment of the present application provides a method for optimizing hyperparameters in a machine learning model, including: sending a task configuration file to a server, wherein the task configuration file includes hyperparameters, a first algorithm type, and a parameter search range, and the server Run the hyperparameter optimization task to calculate the candidate value of the hyperparameter according to the parameter search range and the first hyperparameter optimization algorithm corresponding to the first algorithm type; obtain the candidate hyperparameter from the server value; verify the candidate value of the hyperparameter, and update the task configuration file according to the verification result; send the updated task configuration file to the server, wherein the server according to the updated The task configuration file continues to run the hyperparameter optimization task to obtain new candidate values; after the hyperparameter optimization task runs, determine the optimal value of the hyperparameter according to the verification results of each candidate value.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to a method and device for optimizing hyperparameters in a machine learning model. Background technique [0002] When using machine learning to complete tasks such as image recognition and natural language processing, it is necessary to train the machine learning model first, and the training process includes the process of adjusting the parameters of the machine learning model. The parameters of machine learning models mainly include hyperparameters and ordinary parameters. Among them, hyperparameters are parameters whose values ​​are set before starting the learning process, rather than parameter data obtained through training. Hyperparameters define higher-level concepts about machine learning models, such as network depth, learning rate, etc., and the choice of hyperparameters has a great impact on the final effect of machine learning models. [0003] In the pro...

AI Technical Summary

Problems solved by technology

In addition, the hyperparameter tuning request is single. The user pre-sets the hyperparameter search range and times. During this tuning process, the user cannot interact with the parameter tuning service system to dynamically adjust the hyperparameter search range. The entire parameter tuning process cannot be adjusted manually, the efficiency is low, and it is easy to fall into local optimum

Moreover, each parameter adjustment task is restarted, and the results of historical tasks are not used, which takes a long time

Images