Gaussian Process Optimization with Mutual Information
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 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 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.
Cite
Text
Contal et al. "Gaussian Process Optimization with Mutual Information." International Conference on Machine Learning, 2014.Markdown
[Contal et al. "Gaussian Process Optimization with Mutual Information." International Conference on Machine Learning, 2014.](https://mlanthology.org/icml/2014/contal2014icml-gaussian/)BibTeX
@inproceedings{contal2014icml-gaussian,
title = {{Gaussian Process Optimization with Mutual Information}},
author = {Contal, Emile and Perchet, Vianney and Vayatis, Nicolas},
booktitle = {International Conference on Machine Learning},
year = {2014},
pages = {253-261},
volume = {32},
url = {https://mlanthology.org/icml/2014/contal2014icml-gaussian/}
}