Bayesian Optimization with Exponential Convergence
Machine Learning
2016-04-06 v1 Machine Learning
Abstract
This paper presents a Bayesian optimization method with exponential convergence without the need of auxiliary optimization and without the delta-cover sampling. Most Bayesian optimization methods require auxiliary optimization: an additional non-convex global optimization problem, which can be time-consuming and hard to implement in practice. Also, the existing Bayesian optimization method with exponential convergence requires access to the delta-cover sampling, which was considered to be impractical. Our approach eliminates both requirements and achieves an exponential convergence rate.
Cite
@article{arxiv.1604.01348,
title = {Bayesian Optimization with Exponential Convergence},
author = {Kenji Kawaguchi and Leslie Pack Kaelbling and Tomás Lozano-Pérez},
journal= {arXiv preprint arXiv:1604.01348},
year = {2016}
}
Comments
In NIPS 2015 (Advances in Neural Information Processing Systems 2015)