An investigation on the use of Large Language Models for hyperparameter tuning in Evolutionary Algorithms

TL;DR

This paper explores using Large Language Models to automate hyperparameter tuning in Evolutionary Algorithms, specifically for step-size adaptation in (1+1)-ES, showing promising initial results.

Contribution

It introduces a novel approach of leveraging LLMs for real-time hyperparameter recommendations in Evolution Strategies, a previously unexplored application.

Findings

LLMs can analyze optimization logs effectively.

Preliminary results show potential for hyperparameter optimization.

Encourages further research in LLM-based optimization methods.

Abstract

Hyperparameter optimization is a crucial problem in Evolutionary Computation. In fact, the values of the hyperparameters directly impact the trajectory taken by the optimization process, and their choice requires extensive reasoning by human operators. Although a variety of self-adaptive Evolutionary Algorithms have been proposed in the literature, no definitive solution has been found. In this work, we perform a preliminary investigation to automate the reasoning process that leads to the choice of hyperparameter values. We employ two open-source Large Language Models (LLMs), namely Llama2-70b and Mixtral, to analyze the optimization logs online and provide novel real-time hyperparameter recommendations. We study our approach in the context of step-size adaptation for (1+1)-ES. The results suggest that LLMs can be an effective method for optimizing hyperparameters in Evolution Strategies, encouraging further research in this direction.