Max-value Entropy Search for Efficient Bayesian Optimization

arXiv1703.01968MaRDI QIDQ6283963

Author name not available (Why is that?)

Publication date: 6 March 2017

Abstract: Entropy Search (ES) and Predictive Entropy Search (PES) are popular and empirically successful Bayesian Optimization techniques. Both rely on a compelling information-theoretic motivation, and maximize the information gained about the $argmax$ of the unknown function; yet, both are plagued by the expensive computation for estimating entropies. We propose a new criterion, Max-value Entropy Search (MES), that instead uses the information about the maximum function value. We show relations of MES to other Bayesian optimization methods, and establish a regret bound. We observe that MES maintains or improves the good empirical performance of ES/PES, while tremendously lightening the computational burden. In particular, MES is much more robust to the number of samples used for computing the entropy, and hence more efficient for higher dimensional problems.

Has companion code repository: https://github.com/SK-tklab/BayesianOptimization

This page was built for publication: Max-value Entropy Search for Efficient Bayesian Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6283963)