Escaping local minima with derivative-free methods: a numerical investigation

TL;DR

This paper evaluates the effectiveness of the derivative-free solver Py-BOBYQA for global optimization, demonstrating its competitiveness and advantages over other methods in various noisy and smooth problem settings.

Contribution

It introduces an algorithmic improvement to Py-BOBYQA and provides a comprehensive numerical comparison with other global optimization methods.

Findings

Py-BOBYQA is competitive across different accuracy and budget regimes.

Variants of Py-BOBYQA excel in high-accuracy, noisy, and smooth problem settings.

Preliminary insights into the performance of other global solvers with default configurations.

Abstract

We apply a state-of-the-art, local derivative-free solver, Py-BOBYQA, to global optimization problems, and propose an algorithmic improvement that is beneficial in this context. Our numerical findings are illustrated on a commonly-used but small-scale test set of global optimization problems and associated noisy variants, and on hyperparameter tuning for the machine learning test set MNIST. As Py-BOBYQA is a model-based trust-region method, we compare mostly (but not exclusively) with other global optimization methods for which (global) models are important, such as Bayesian optimization and response surface methods; we also consider state-of-the-art representative deterministic and stochastic codes, such as DIRECT and CMA-ES. As a heuristic for escaping local minima, we find numerically that Py-BOBYQA is competitive with global optimization solvers for all accuracy/budget regimes, in both smooth and noisy settings. In particular, Py-BOBYQA variants are best performing for smooth and multiplicative noise problems in high-accuracy regimes. As a by-product, some preliminary conclusions can be drawn on the relative performance of the global solvers we have tested with default settings.