Learning from Distributed Users in Contextual Linear Bandits Without Sharing the Context

Authors: Osama Hanna, Lin Yang, Christina Fragouli

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

Reproducibility Variable Result LLM Response
Research Type Theoretical 3. If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]. Also, from the abstract: "achieving nearly the same regret bound as if the contexts were directly observable. The former bound improves upon existing bounds by a log(T) factor, while the latter achieves information theoretical tightness."
Researcher Affiliation Academia Osama A. Hanna University of California, Los Angeles ohanna@ucla.edu Lin F. Yang University of California, Los Angeles linyang@ucla.edu Christina Fragouli University of California, Los Angeles christina.fragouli@ucla.edu
Pseudocode Yes Algorithm 1 Communication efficient for contextual linear bandits with known distribution (...) Algorithm 2 Communication efficient for contextual linear bandits with unknown distribution
Open Source Code No 3. If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]. The paper does not provide any links or explicit statements about open-source code for the described methodology.
Open Datasets No 3. If you ran experiments... (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]. The paper is theoretical and describes contexts being "generated from a distribution" but does not specify or provide access information for any publicly available or open dataset used for training.
Dataset Splits No The paper explicitly states "N/A" for running experiments in its checklist and does not discuss any training, validation, or test dataset splits.
Hardware Specification No The paper explicitly states "N/A" for running experiments in its checklist and does not mention any specific hardware used for computations or experiments.
Software Dependencies No The paper explicitly states "N/A" for running experiments in its checklist and does not list any specific software dependencies with version numbers.
Experiment Setup No The paper explicitly states "N/A" for running experiments in its checklist and does not describe any experimental setup details such as hyperparameters or training configurations.