Gaussian process optimization with mutual information

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

Abstract

In this paper, we analyze a generic algorithm scheme for sequential global optimization using Gaussian processes. The upper bounds we derive on the cumulative regret for this generic algo-rithm improve by an exponential factor the previously known bounds for algorithms like GP- UCB. We also introduce the novel Gaussian Process Mutual Information algorithm (GP-MI), which significantly improves further these upper bounds for the cumulative regret. We confirm the efficiency of this algorithm on synthetic and real tasks against the natural competitor, GP-UCB, and also the Expected Improvement heuristic.

Original languageEnglish
Title of host publication31st International Conference on Machine Learning, ICML 2014
PublisherInternational Machine Learning Society (IMLS)
Pages1515-1523
Number of pages9
ISBN (Electronic)9781634393973
Publication statusPublished - 1 Jan 2014
Externally publishedYes
Event31st International Conference on Machine Learning, ICML 2014 - Beijing, China
Duration: 21 Jun 201426 Jun 2014

Publication series

Name31st International Conference on Machine Learning, ICML 2014
Volume2

Conference

Conference31st International Conference on Machine Learning, ICML 2014
Country/TerritoryChina
CityBeijing
Period21/06/1426/06/14

Fingerprint

Dive into the research topics of 'Gaussian process optimization with mutual information'. Together they form a unique fingerprint.

Cite this