Bayesian Optimization with Unknown Constraints

TL;DR

This paper extends Bayesian optimization techniques to handle problems with unknown, noisy constraints, enabling more effective optimization in complex real-world scenarios with independent evaluations.

Contribution

It introduces a general framework for Bayesian optimization with unknown, noisy constraints, applicable to various practical optimization problems.

Findings

Effective optimization of online latent Dirichlet allocation with constraints

Tuning neural networks under memory constraints

Optimizing Hamiltonian Monte Carlo within fixed time constraints

Abstract

Recent work on Bayesian optimization has shown its effectiveness in global optimization of difficult black-box objective functions. Many real-world optimization problems of interest also have constraints which are unknown a priori. In this paper, we study Bayesian optimization for constrained problems in the general case that noise may be present in the constraint functions, and the objective and constraints may be evaluated independently. We provide motivating practical examples, and present a general framework to solve such problems. We demonstrate the effectiveness of our approach on optimizing the performance of online latent Dirichlet allocation subject to topic sparsity constraints, tuning a neural network given test-time memory constraints, and optimizing Hamiltonian Monte Carlo to achieve maximal effectiveness in a fixed time, subject to passing standard convergence diagnostics.