An Adaptive Re-evaluation Method for Evolution Strategy under Additive Noise

TL;DR

This paper introduces an adaptive re-evaluation method for CMA-ES that optimally determines the number of re-evaluations under additive Gaussian noise, improving optimization success rates.

Contribution

The paper presents a novel theoretical approach to adaptively select re-evaluation counts in CMA-ES for noisy functions, based on derived bounds and noise estimation.

Findings

Our method outperforms existing noise-handling techniques in hitting near-optimal solutions.

It adapts re-evaluation numbers effectively across different noise levels and problem dimensions.

Experimental results show increased probability of successful optimization.

Abstract

The Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) is one of the most advanced algorithms in numerical black-box optimization. For noisy objective functions, several approaches were proposed to mitigate the noise, e.g., re-evaluations of the same solution or adapting the population size. In this paper, we devise a novel method to adaptively choose the optimal re-evaluation number for function values corrupted by additive Gaussian white noise. We derive a theoretical lower bound of the expected improvement achieved in one iteration of CMA-ES, given an estimation of the noise level and the Lipschitz constant of the function's gradient. Solving for the maximum of the lower bound, we obtain a simple expression of the optimal re-evaluation number. We experimentally compare our method to the state-of-the-art noise-handling methods for CMA-ES on a set of artificial test functions across various noise levels, optimization budgets, and dimensionality. Our method demonstrates significant advantages in terms of the probability of hitting near-optimal function values.