How Does Variance Shape the Regret in Contextual Bandits?

Authors: Zeyu Jia, Jian Qian, Alexander Rakhlin, Chen-Yu Wei

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We prove that a regret of Ω(..., we derive a nearly matching upper bound O(...), Theorem 4.1 (Main lower bound), Algorithm 1 Var CB (Variance-aware Contextual Bandits), The proof is provided in Appendix F.
Researcher Affiliation Academia Zeyu Jia Massachusetts Institute of Technology zyjia@mit.edu Jian Qian Massachusetts Institute of Technology jianqian@mit.edu Alexander Rakhlin Massachusetts Institute of Technology rakhlin@mit.edu Chen-Yu Wei University of Virginia chenyu.wei@virginia.edu
Pseudocode Yes Algorithm 1 Var CB (Variance-aware Contextual Bandits), Algorithm 2 Algorithm for Heteroscedastic Noise, Algorithm 3 Dist Var CB (Distributional Variance-aware Contextual Bandits), Algorithm 4 Prod-based online regression oracle, Algorithm 5 Var UCB, Algorithm 6 Variance Sensitive Square CB for Zero-One Noise
Open Source Code No The paper does not contain any explicit statements about releasing source code for the described methodology or links to code repositories.
Open Datasets No This paper is theoretical and does not use or reference any datasets for training or public access.
Dataset Splits No This paper is theoretical and does not involve empirical experiments requiring dataset splits.
Hardware Specification No This paper is theoretical and does not include any experimental results that would require a description of hardware specifications.
Software Dependencies No This paper is theoretical and does not describe any experiments that would require specific software dependencies or their version numbers.
Experiment Setup No This paper is theoretical and does not include an experimental setup, hyperparameters, or training configurations.