English

Gaussian Process Optimization with Mutual Information

Machine Learning 2015-06-09 v3 Machine Learning

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.

Keywords

Cite

@article{arxiv.1311.4825,
  title  = {Gaussian Process Optimization with Mutual Information},
  author = {Emile Contal and Vianney Perchet and Nicolas Vayatis},
  journal= {arXiv preprint arXiv:1311.4825},
  year   = {2015}
}

Comments

Proceedings of The 31st International Conference on Machine Learning (ICML 2014)

R2 v1 2026-06-22T02:10:38.822Z