Natural Evolution Strategy for Unconstrained and Implicitly Constrained Problems with Ridge Structure

TL;DR

This paper introduces FM-NES, a new natural evolution strategy that accelerates optimization on ridge-structured problems by incorporating a rank-one update, improving performance on unconstrained and implicitly constrained black-box problems.

Contribution

The paper proposes FM-NES, an enhanced natural evolution strategy with a rank-one update, addressing slow movement issues on ridge structures in black-box optimization.

Findings

FM-NES outperforms DX-NES-IC on ridge-structured problems.

FM-NES matches DX-NES-IC performance on other problems.

FM-NES surpasses xNES and CMA-ES in benchmark tests.

Abstract

In this paper, we propose a new natural evolution strategy for unconstrained black-box function optimization (BBFO) problems and implicitly constrained BBFO problems. BBFO problems are known to be difficult because explicit representations of objective functions are not available. Implicit constraints make the problems more difficult because whether or not a solution is feasible is revealed when the solution is evaluated with the objective function. DX-NES-IC is one of the promising methods for implicitly constrained BBFO problems. DX-NES-IC has shown better performance than conventional methods on implicitly constrained benchmark problems. However, DX-NES-IC has a problem in that the moving speed of the probability distribution is slow on ridge structure. To address the problem, we propose the Fast Moving Natural Evolution Strategy (FM-NES) that accelerates the movement of the probability distribution on ridge structure by introducing the rank-one update into DX-NES-IC. The rank-one update is utilized in CMA-ES. Since naively introducing the rank-one update makes the search performance deteriorate on implicitly constrained problems, we propose a condition of performing the rank-one update. We also propose to reset the shape of the probability distribution when an infeasible solution is sampled at the first time. In numerical experiments using unconstrained and implicitly constrained benchmark problems, FM-NES showed better performance than DX-NES-IC on problems with ridge structure and almost the same performance as DX-NES-IC on the others. Furthermore, FM-NES outperformed xNES, CMA-ES, xNES with the resampling technique, and CMA-ES with the resampling technique.