Tracing the Interactions of Modular CMA-ES Configurations Across Problem Landscapes

TL;DR

This study uses algorithm footprints to analyze how different modular CMA-ES configurations interact with problem features across benchmark landscapes, revealing insights into performance variability and guiding configuration decisions.

Contribution

It introduces the use of algorithm footprints to interpret the interactions between modular CMA-ES configurations and problem landscapes, enhancing understanding of performance differences.

Findings

Shared behavioral patterns across configurations due to common interactions

Distinct behaviors driven by specific problem features

Algorithm footprints improve interpretability and configuration guidance

Abstract

This paper leverages the recently introduced concept of algorithm footprints to investigate the interplay between algorithm configurations and problem characteristics. Performance footprints are calculated for six modular variants of the CMA-ES algorithm (modCMA), evaluated on 24 benchmark problems from the BBOB suite, across two-dimensional settings: 5-dimensional and 30-dimensional. These footprints provide insights into why different configurations of the same algorithm exhibit varying performance and identify the problem features influencing these outcomes. Our analysis uncovers shared behavioral patterns across configurations due to common interactions with problem properties, as well as distinct behaviors on the same problem driven by differing problem features. The results demonstrate the effectiveness of algorithm footprints in enhancing interpretability and guiding configuration choices.