Robust and private stochastic linear bandits

Authors: Vasileios Charisopoulos, Hossein Esfandiari, Vahab Mirrokni

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we study the stochastic linear bandit problem under the additional requirements of differential privacy, robustness and batched observations. ... We present differentially private and robust variants of the arm elimination algorithm using logarithmic batch queries under two privacy models and provide regret bounds in both settings.
Researcher Affiliation Collaboration 1Operations Research & Information Engineering, Cornell University. Part of this work was completed while the author was with Google. 2Google Research. Correspondence to: Vasileios Charisopoulos <vc333@cornell.edu>.
Pseudocode Yes Algorithm 1 Robust arm elimination and Algorithm 2 Filter(S := {Xi}m i=1, λ)
Open Source Code No The paper does not provide any concrete access to source code, such as a repository link or an explicit code release statement, for the methodology described.
Open Datasets No The paper is theoretical and describes a stochastic linear bandit problem model rather than empirical experiments on a dataset, so there is no mention of a publicly available dataset for training.
Dataset Splits No The paper is theoretical and does not involve empirical evaluation on datasets, so no specific dataset split information (like training, validation, or test splits) is provided.
Hardware Specification No The paper is theoretical and focuses on algorithm design and theoretical guarantees; therefore, it does not describe specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not provide details on software dependencies or specific version numbers for replication.
Experiment Setup No The paper describes the theoretical model and algorithmic details, but it does not provide specific experimental setup details such as hyperparameter values, training configurations, or system-level settings for empirical evaluation.