Adaptive Generation-Based Evolution Control for Gaussian Process Surrogate Models

TL;DR

This paper introduces an adaptive method to improve surrogate-assisted Covariance Matrix Adaptation Evolution Strategy (CMA-ES) by dynamically adjusting the number of generations using Gaussian process models, leading to minor performance gains.

Contribution

It proposes an adaptive procedure for surrogate model usage in S-CMA-ES, enhancing the existing fixed-lifetime approach with performance-based adjustments.

Findings

Minor improvement with larger surrogate lifelengths

Performance varies depending on the surrogate measure used

Adaptive approach slightly outperforms fixed strategies

Abstract

The interest in accelerating black-box optimizers has resulted in several surrogate model-assisted version of the Covariance Matrix Adaptation Evolution Strategy, a state-of-the-art continuous black-box optimizer. The version called Surrogate CMA-ES uses Gaussian processes or random forests surrogate models with a generation-based evolution control. This paper presents an adaptive improvement for S-CMA-ES based on a general procedure introduced with the s*ACM-ES algorithm, in which the number of generations using the surrogate model before retraining is adjusted depending on the performance of the last instance of the surrogate. Three algorithms that differ in the measure of the surrogate model's performance are evaluated on the COCO/BBOB framework. The results show a minor improvement on S-CMA-ES with constant model lifelengths, especially when larger lifelengths are considered.