Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits
Keywords: contextual linear bandit, online batch learning
TL;DR: We establish near-optimal batch-regret trade-off for contextual linear bandit problem.
Abstract: We study the optimal batch-regret tradeoff for batch linear contextual bandits. For this problem, we design batch learning algorithms and prove that they achieve the optimal regret bounds (up to logarithmic factors) for any batch number $M$, number of actions $K$, time horizon $T$, and dimension $d$. Therefore, we establish the \emph{full-parameter-range} (almost) optimal batch-regret tradeoff for the batch linear contextual bandit problem.
Along our analysis, we also prove a new matrix concentration inequality with dependence on their dynamic upper bounds, which, to the best of our knowledge, is the first of its kind in literature and maybe of independent interest.
Supplementary Material: zip
Primary Area: learning 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.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 8183
Loading