Alternative Restart Strategies for CMA-ES

TL;DR

This paper introduces new restart strategies for CMA-ES, including decreasing initial step-size with increasing population and adaptive budget allocation, validated on benchmarks and real-world problems.

Contribution

It proposes two novel restart strategies for CMA-ES, enhancing its performance on multi-modal functions and demonstrating their effectiveness on benchmarks and real-world problems.

Findings

Both strategies outperform standard CMA-ES on BBOB benchmark.

Strategies show robustness on spacecraft trajectory optimization.

Adaptive scheme improves computational efficiency.

Abstract

This paper focuses on the restart strategy of CMA-ES on multi-modal functions. A first alternative strategy proceeds by decreasing the initial step-size of the mutation while doubling the population size at each restart. A second strategy adaptively allocates the computational budget among the restart settings in the BIPOP scheme. Both restart strategies are validated on the BBOB benchmark; their generality is also demonstrated on an independent real-world problem suite related to spacecraft trajectory optimization.