Standard Acquisition Is Sufficient for Asynchronous Bayesian Optimization

TL;DR

This paper demonstrates that simple standard acquisition functions like UCB are sufficient for asynchronous Bayesian optimization, challenging the need for complex diversity-enforcing methods and showing they often underperform.

Contribution

The paper provides a theoretical and empirical analysis showing standard acquisition functions can match or outperform complex methods in asynchronous Bayesian optimization.

Findings

Standard acquisition functions achieve theoretical guarantees similar to sequential methods.

Intermediate posterior updates are sufficient to prevent redundant queries.

Simple methods outperform or match complex diversity-enforcing approaches in experiments.

Abstract

Asynchronous Bayesian optimization is widely used for gradient-free optimization in domains with independent parallel experiments and varying evaluation times. Existing methods posit that standard acquisitions lead to redundant and repeated queries, proposing complex solutions to enforce diversity in queries. Challenging this fundamental premise, we show that methods, like the Upper Confidence Bound, can in fact achieve theoretical guarantees essentially equivalent to those of sequential Thompson sampling. A conceptual analysis of asynchronous Bayesian optimization reveals that existing works neglect intermediate posterior updates, which we find to be generally sufficient to avoid redundant queries. Further investigation shows that by penalizing busy locations, diversity-enforcing methods can over-explore in asynchronous settings, reducing their performance. Our extensive experiments demonstrate that simple standard acquisition functions match or outperform purpose-built asynchronous methods across synthetic and real-world tasks.