A hyper-parameter optimization method and device in a machine learning model

Abstract

The embodiment of the invention provides a hyper-parameter optimization method in a machine learning model. The method comprises the steps of sending a task configuration file to a server, wherein thetask configuration file comprises a hyper-parameter, a first algorithm type and a parameter search range, and the server runs a hyper-parameter optimization task so as to calculate a candidate valueof the hyper-parameter according to the parameter search range and a first hyper-parameter optimization algorithm corresponding to the first algorithm type; obtaining a candidate value of the hyper-parameter from the server; verifying the candidate value of the hyper-parameter, and updating the task configuration file according to a verification result; sending the updated task configuration fileto the server, wherein the server continues to run the hyper-parameter optimization task according to the updated task configuration file, and a new candidate value is obtained; and after the operation of the hyper-parameter optimization task is finished, determining an optimal value of the hyper-parameter according to a verification result of each candidate value.

Description

Technical field [0001] This application relates to the field of artificial intelligence, and 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, the machine learning model needs to be trained first. The training process includes the process of adjusting the parameters of the machine learning model. The parameters of the machine learning model 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 the machine learning model, such as network depth, learning rate, etc., and the choice of hyperparameters has a great impact on the final effect of the machine learning model. [0003] In the process of ma...

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