Related papers: A Study of Bayesian Neural Network Surrogates for Bayesian Optimization

A Study of Bayesian Neural Network Surrogates for Bayesian Optimization

URL: http://arxiv.org/abs/2305.20028v2
Date: Wed, 8 May 2024 10:30:22 GMT
Title: A Study of Bayesian Neural Network Surrogates for Bayesian Optimization
Authors: Yucen Lily Li, Tim G. J. Rudner, Andrew Gordon Wilson,
Abstract summary: Bayesian neural networks (BNNs) have recently become practical function approximators. We study BNNs as alternatives to standard GP surrogates for optimization.
Score: 46.97686790714025
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Bayesian optimization is a highly efficient approach to optimizing objective functions which are expensive to query. These objectives are typically represented by Gaussian process (GP) surrogate models which are easy to optimize and support exact inference. While standard GP surrogates have been well-established in Bayesian optimization, Bayesian neural networks (BNNs) have recently become practical function approximators, with many benefits over standard GPs such as the ability to naturally handle non-stationarity and learn representations for high-dimensional data. In this paper, we study BNNs as alternatives to standard GP surrogates for optimization. We consider a variety of approximate inference procedures for finite-width BNNs, including high-quality Hamiltonian Monte Carlo, low-cost stochastic MCMC, and heuristics such as deep ensembles. We also consider infinite-width BNNs, linearized Laplace approximations, and partially stochastic models such as deep kernel learning. We evaluate this collection of surrogate models on diverse problems with varying dimensionality, number of objectives, non-stationarity, and discrete and continuous inputs. We find: (i) the ranking of methods is highly problem dependent, suggesting the need for tailored inductive biases; (ii) HMC is the most successful approximate inference procedure for fully stochastic BNNs; (iii) full stochasticity may be unnecessary as deep kernel learning is relatively competitive; (iv) deep ensembles perform relatively poorly; (v) infinite-width BNNs are particularly promising, especially in high dimensions.