Scalable Thompson Sampling via Optimal Transport
Abstract
Thompson sampling (TS) is a class of algorithms for sequential decision-making, which requires maintaining a posterior distribution over a model. However, calculating exact posterior distributions is intractable for all but the simplest models. Consequently, efficient computation of an approximate posterior distribution is a crucial problem for scalable TS with complex models, such as neural networks. In this paper, we use distribution optimization techniques to approximate the posterior distribution, solved via Wasserstein gradient flows. Based on the framework, a principled particle-optimization algorithm is developed for TS to approximate the posterior efficiently. Our approach is scalable and does not make explicit distribution assumptions on posterior approximations. Extensive experiments on both synthetic data and real large-scale data demonstrate the superior performance of the proposed methods.
Cite
@article{arxiv.1902.07239,
title = {Scalable Thompson Sampling via Optimal Transport},
author = {Ruiyi Zhang and Zheng Wen and Changyou Chen and Lawrence Carin},
journal= {arXiv preprint arXiv:1902.07239},
year = {2019}
}
Comments
Infer to Control Workshop on Probabilistic Reinforcement Learning and Structured Control at NIPS 2018; Long version accepted by AISTATS 2019