CUED Publications database

Parallel and distributed thompson sampling for large-scale accelerated exploration of chemical space

Hernández-Lobato, JM and Requeima, J and Pyzer-Knapp, EO and Aspuru-Guzik, A (2017) Parallel and distributed thompson sampling for large-scale accelerated exploration of chemical space. 34th International Conference on Machine Learning, ICML 2017, 3. pp. 2325-2334.

Full text not available from this repository.

Abstract

Copyright 2017 by the author(s). Chemical space is so large that brute force searches for new interesting molecules arc in-feasible. High-throughput virtual screening via computer cluster simulations can speed up the discovery process by collecting very large amounts of data in parallel, e.g., up to hundreds or thousands of parallel measurements. Bayesian optimization (BO) can produce additional acceleration by sequentially identifying the most useful simulations or experiments to be performed next. However, current BO methods cannot scale to the large numbers of parallel measurements and the massive libraries of molecules currently used in high-throughput screening. Here, we propose a scalable solution based on a parallel and distributed implementation of Thompson sampling (PDTS). We show that, in small scale problems, PDTS performs similarly as parallel expected improvement (EI), a batch version of the most widely used BO heuristic. Additionally, in settings where parallel EI does not scale, PDTS outperforms other scalable baselines such as a greedy search, c-grcedy approaches and a random search method. These results show that PDTS is a successful solution for large-scale par-allel BO.

Item Type: Article
Uncontrolled Keywords: stat.ML stat.ML
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:56
Last Modified: 17 Sep 2020 02:44
DOI: