Solving Black-Box Optimization Challenge via Learning Search Space Partition for Local Bayesian Optimization

TL;DR

This paper presents SPBOpt, a novel approach for black-box optimization that learns to partition the search space for improved local Bayesian optimization, achieving third place in a NeurIPS challenge.

Contribution

The paper introduces a new algorithm, SPBOpt, which utilizes learned search space partitioning to enhance local Bayesian optimization under limited budget conditions.

Findings

Ranked third in NeurIPS 2020 challenge.

Effective search space partitioning improves optimization performance.

Multi-task Bayesian optimization fine-tunes algorithm hyperparameters.

Abstract

Black-box optimization is one of the vital tasks in machine learning, since it approximates real-world conditions, in that we do not always know all the properties of a given system, up to knowing almost nothing but the results. This paper describes our approach to solving the black-box optimization challenge at NeurIPS 2020 through learning search space partition for local Bayesian optimization. We describe the task of the challenge as well as our algorithm for low budget optimization that we named \texttt{SPBOpt}. We optimize the hyper-parameters of our algorithm for the competition finals using multi-task Bayesian optimization on results from the first two evaluation settings. Our approach has ranked third in the competition finals.