Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations

December 2016

Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations

Authors:

K. Kandasamy, G. Dasarathy, J. Oliva, J. Schneider, and B. Poczos
Conference Paper
Proceedings of (NeurIPS) Neural Information Processing Systems

Abstract:

In many scientific and engineering applications, we are tasked with the maximisation of an expensive to evaluate black box function f. Traditional settings for this problem assume just the availability of this single function. However, in many cases, cheap approximations to f may be obtainable. For example, the expensive real world behaviour of a robot can be approximated by a cheap computer simulation. We can use these approximations to eliminate low function value regions cheaply and use the expensive evaluations of f in a small but promising region and speedily identify the optimum. We formalise this task as a \emph{multi-fidelity} bandit problem where the target function and its approximations are sampled from a Gaussian process. We develop MF-GP-UCB, a novel method based on upper confidence bound techniques. In our theoretical analysis we demonstrate that it exhibits precisely the above behaviour, and achieves better regret than strategies which ignore multi-fidelity information. Empirically, MF-GP-UCB outperforms such naive strategies and other multi-fidelity methods on several synthetic and real experiments.
@conference{Kandasamy-2016-119746,
author = {K. Kandasamy And G. Dasarathy And J. Oliva And J. Schneider And B. Poczos},
title = {Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations},
booktitle = {Proceedings of (NeurIPS) Neural Information Processing Systems},
year = {2016},
month = {December},
pages = {1000 - 1008},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.