On Hyper-parameter Tuning for Stochastic Optimization Algorithms

TL;DR

This paper introduces a reinforcement learning-based framework for hyper-parameter tuning in stochastic optimization algorithms, aiming to improve tuning efficiency and effectiveness across various problem types.

Contribution

It presents the first algorithmic framework using reinforcement learning to automatically tune hyper-parameters of stochastic algorithms, modeling the process as a Markov decision process.

Findings

The framework effectively tunes both continuous and discrete hyper-parameters.

It requires less running time than Bayesian optimization methods.

It can serve as a standard tool for hyper-parameter tuning in stochastic algorithms.

Abstract

This paper proposes the first-ever algorithmic framework for tuning hyper-parameters of stochastic optimization algorithm based on reinforcement learning. Hyper-parameters impose significant influences on the performance of stochastic optimization algorithms, such as evolutionary algorithms (EAs) and meta-heuristics. Yet, it is very time-consuming to determine optimal hyper-parameters due to the stochastic nature of these algorithms. We propose to model the tuning procedure as a Markov decision process, and resort the policy gradient algorithm to tune the hyper-parameters. Experiments on tuning stochastic algorithms with different kinds of hyper-parameters (continuous and discrete) for different optimization problems (continuous and discrete) show that the proposed hyper-parameter tuning algorithms do not require much less running times of the stochastic algorithms than bayesian optimization method. The proposed framework can be used as a standard tool for hyper-parameter tuning in stochastic algorithms.