A Reduction from Linear Contextual Bandits Lower Bounds to Estimations Lower Bounds

Authors: Jiahao He, Jiheng Zhang, Rachel Q. Zhang

ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we complete the reverse direction by establishing the necessity. In particular, we provide a generic transformation from algorithms for linear contextual bandits to estimators for linear models, and show that algorithm regrets dominate estimation errors of their induced estimators, i.e., low-regret algorithms must imply accurate estimators. Moreover, our analysis reduces the regret lower bound to an estimation error, bridging the lower bound analysis in linear contextual bandit problems and linear regression.
Researcher Affiliation Academia 1Department of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong, China.
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks. The content is theoretical, focusing on mathematical derivations and proofs.
Open Source Code No The paper does not provide any concrete access information (specific link, explicit statement of release) to open-source code for the methodology described.
Open Datasets No The paper is theoretical and does not use or provide access to any public or open datasets for training purposes. It discusses theoretical properties of context vectors (zt) under various distributions as assumptions for its analysis.
Dataset Splits No The paper is theoretical and does not describe empirical experiments involving dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any hardware used for running experiments.
Software Dependencies No The paper is theoretical and does not mention any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details, hyperparameters, or system-level training settings.