Asynchronous Parallel Bayesian Optimisation via Thompson Sampling

April 2018

Asynchronous Parallel Bayesian Optimisation via Thompson Sampling

Authors:

K. Kandasamy, A. Krishnamurthy, J. Schneider, and B. Poczos

Abstract:

We design and analyse variations of the classical Thompson sampling (TS) procedure for Bayesian optimisation (BO) in settings where function evaluations are expensive, but can be performed in parallel. Our theoretical analysis shows that a direct application of the sequential Thompson sampling algorithm in either synchronous or asynchronous parallel settings yields a surprisingly powerful result: making n evaluations distributed among M workers is essentially equivalent to performing n evaluations in sequence. Further, by modeling the time taken to complete a function evaluation, we show that, under a time constraint, asynchronously parallel TS achieves asymptotically lower regret than both the synchronous and sequential versions. These results are complemented by an experimental analysis, showing that asynchronous TS outperforms a suite of existing parallel BO algorithms in simulations and in a hyper-parameter tuning application in convolutional neural networks. In addition to these, the proposed procedure is conceptually and computationally much simpler than existing work for parallel BO.
@conference{Kandasamy-2018-119740,
author = {K. Kandasamy And A. Krishnamurthy And J. Schneider And B. Poczos},
title = {Asynchronous Parallel Bayesian Optimisation via Thompson Sampling},
booktitle = {Proceedings of 21st International Conference on Artificial Intelligence and Statistics (AISTATS '18)},
year = {2018},
month = {April},
volume = {84},
pages = {133 - 142},
}
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.