Thompson Sampling for High-Dimensional Sparse Linear Contextual Bandits
From MaRDI portal
Publication:6416882
arXiv2211.05964MaRDI QIDQ6416882
Author name not available (Why is that?)
Publication date: 10 November 2022
Abstract: We consider the stochastic linear contextual bandit problem with high-dimensional features. We analyze the Thompson sampling algorithm using special classes of sparsity-inducing priors (e.g., spike-and-slab) to model the unknown parameter and provide a nearly optimal upper bound on the expected cumulative regret. To the best of our knowledge, this is the first work that provides theoretical guarantees of Thompson sampling in high-dimensional and sparse contextual bandits. For faster computation, we use variational inference instead of Markov Chain Monte Carlo (MCMC) to approximate the posterior distribution. Extensive simulations demonstrate the improved performance of our proposed algorithm over existing ones.
Has companion code repository: https://github.com/roysaptaumich/HD-bandit-codes
This page was built for publication: Thompson Sampling for High-Dimensional Sparse Linear Contextual Bandits
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6416882)
