Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space

José Miguel Hernández-Lobato, James Requeima, Edward O. Pyzer-Knapp, Alán Aspuru-Guzik
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:1470-1479, 2017.

Abstract

Chemical space is so large that brute force searches for new interesting molecules are infeasible. 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, $\epsilon$-greedy approaches and a random search method. These results show that PDTS is a successful solution for large-scale parallel BO.

Cite this Paper


BibTeX
@InProceedings{pmlr-v70-hernandez-lobato17a, title = {Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space}, author = {Jos{\'e} Miguel Hern{\'a}ndez-Lobato and James Requeima and Edward O. Pyzer-Knapp and Al{\'a}n Aspuru-Guzik}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {1470--1479}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/hernandez-lobato17a/hernandez-lobato17a.pdf}, url = {https://proceedings.mlr.press/v70/hernandez-lobato17a.html}, abstract = {Chemical space is so large that brute force searches for new interesting molecules are infeasible. 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, $\epsilon$-greedy approaches and a random search method. These results show that PDTS is a successful solution for large-scale parallel BO.} }
Endnote
%0 Conference Paper %T Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space %A José Miguel Hernández-Lobato %A James Requeima %A Edward O. Pyzer-Knapp %A Alán Aspuru-Guzik %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-hernandez-lobato17a %I PMLR %P 1470--1479 %U https://proceedings.mlr.press/v70/hernandez-lobato17a.html %V 70 %X Chemical space is so large that brute force searches for new interesting molecules are infeasible. 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, $\epsilon$-greedy approaches and a random search method. These results show that PDTS is a successful solution for large-scale parallel BO.
APA
Hernández-Lobato, J.M., Requeima, J., Pyzer-Knapp, E.O. & Aspuru-Guzik, A.. (2017). Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:1470-1479 Available from https://proceedings.mlr.press/v70/hernandez-lobato17a.html.

Related Material