Neural Thompson Sampling

Weitong ZHANG, Dongruo Zhou, Lihong Li, Quanquan Gu

Keywords: Deep Learning, Contextual Bandits, Thompson sampling

Abstract: Thompson Sampling (TS) is one of the most effective algorithms for solving contextual multi-armed bandit problems. In this paper, we propose a new algorithm, called Neural Thompson Sampling, which adapts deep neural networks for both exploration and exploitation. At the core of our algorithm is a novel posterior distribution of the reward, where its mean is the neural network approximator, and its variance is built upon the neural tangent features of the corresponding neural network. We prove that, provided the underlying reward function is bounded, the proposed algorithm is guaranteed to achieve a cumulative regret of $O(T^{1/2})$, which matches the regret of other contextual bandit algorithms in terms of total round number $T$. Experimental comparisons with other benchmark bandit algorithms on various data sets corroborate our theory.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: We propose NeuralTS, a provable neural work-based Thompson sampling algorithm for stochastic contextual bandits.

Code: [ ZeroWeight/NeuralTS](https://github.com/ZeroWeight/NeuralTS) + [ 1 community implementation](https://paperswithcode.com/paper/?openreview=tkAtoZkcUnm)