Gaussian Process Optimization with Mutual Information

Emile Contal, Vianney Perchet, Nicolas Vayatis
Proceedings of the 31st International Conference on Machine Learning, PMLR 32(2):253-261, 2014.

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 this Paper

BibTeX
@InProceedings{pmlr-v32-contal14, title = {Gaussian Process Optimization with Mutual Information}, author = {Contal, Emile and Perchet, Vianney and Vayatis, Nicolas}, booktitle = {Proceedings of the 31st International Conference on Machine Learning}, pages = {253--261}, year = {2014}, editor = {Xing, Eric P. and Jebara, Tony}, volume = {32}, number = {2}, series = {Proceedings of Machine Learning Research}, address = {Bejing, China}, month = {22--24 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v32/contal14.pdf}, url = {https://proceedings.mlr.press/v32/contal14.html}, 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.} }
Endnote
%0 Conference Paper %T Gaussian Process Optimization with Mutual Information %A Emile Contal %A Vianney Perchet %A Nicolas Vayatis %B Proceedings of the 31st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2014 %E Eric P. Xing %E Tony Jebara %F pmlr-v32-contal14 %I PMLR %P 253--261 %U https://proceedings.mlr.press/v32/contal14.html %V 32 %N 2 %X 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.
RIS
TY - CPAPER TI - Gaussian Process Optimization with Mutual Information AU - Emile Contal AU - Vianney Perchet AU - Nicolas Vayatis BT - Proceedings of the 31st International Conference on Machine Learning DA - 2014/06/18 ED - Eric P. Xing ED - Tony Jebara ID - pmlr-v32-contal14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 32 IS - 2 SP - 253 EP - 261 L1 - http://proceedings.mlr.press/v32/contal14.pdf UR - https://proceedings.mlr.press/v32/contal14.html AB - 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. ER -
APA
Contal, E., Perchet, V. & Vayatis, N.. (2014). Gaussian Process Optimization with Mutual Information. Proceedings of the 31st International Conference on Machine Learning, in Proceedings of Machine Learning Research 32(2):253-261 Available from https://proceedings.mlr.press/v32/contal14.html.

Related Material