Max-value entropy search for efficient Bayesian optimization

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

74 Scopus citations

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 arg max 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 perfor-mance 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.

Original languageEnglish
Title of host publication34th International Conference on Machine Learning, ICML 2017
PublisherInternational Machine Learning Society (IMLS)
Pages5530-5543
Number of pages14
ISBN (Electronic)9781510855144
StatePublished - 2017
Externally publishedYes
Event34th International Conference on Machine Learning, ICML 2017 - Sydney, Australia
Duration: 6 Aug 201711 Aug 2017

Publication series

Name34th International Conference on Machine Learning, ICML 2017
Volume7

Conference

Conference34th International Conference on Machine Learning, ICML 2017
Country/TerritoryAustralia
CitySydney
Period6/08/1711/08/17

Fingerprint

Dive into the research topics of 'Max-value entropy search for efficient Bayesian optimization'. Together they form a unique fingerprint.

Cite this