Batch Bayesian Optimization via Particle Gradient Flows

doi:10.1137/23M1549080

Return

Batch Bayesian Optimization via Particle Gradient Flows

2026-01-01

PRE

Enrico Crovini *

Simon L. Cotter

Konstantinos C. Zygalakis

A. Duncan

DOI：10.1137/23M1549080

Original

Original request for help

Save

Abstract

En 中文

Bayesian optimization (BO) methods seek to find global optima of objective functions which are only available as a black-box or are expensive to evaluate. Such methods construct a surrogate model for the objective function, quantifying the uncertainty in that surrogate through Bayesian inference. Objective evaluations are sequentially determined by maximizing an acquisition function at each step. However, this ancilliary optimization problem can be highly nontrivial to solve, due to the nonconcavity of the acquisition function, particularly in the case of batch Bayesian optimization, where multiple points are selected in every step. In this work we reformulate batch BO as an optimization problem over the space of probability measures. We construct a new acquisition function based on multipoint expected improvement, which is concave over the space of probability measures. Practical schemes for solving this ``inner optimization problem arise naturally as gradient flows of this objective function. We demonstrate the efficacy of this new method on different benchmark functions and compare with state-of-the-art batch BO methods.

Keywords:

batch Bayesian optimization

gradient flows

parameter calibration

machine learning