DMCA
Gaussian process optimization with mutual information. arXiv preprint arXiv:1311.4825 (2013)
| Citations: | 2 - 0 self |
BibTeX
@MISC{Contal13gaussianprocess,
author = {Emile Contal and Vianney Perchet and Nicolas Vayatis},
title = {Gaussian process optimization with mutual information. arXiv preprint arXiv:1311.4825},
year = {2013}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper, we analyze a generic algorithm scheme for sequential global opti-mization using Gaussian processes. The upper bounds we derive on the cumulative regret for this generic algorithm 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 fur-ther 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. 1
