Locally Differentially Private (Contextual) Bandits Learning

Authors: Kai Zheng, Tianle Cai, Weiran Huang, Zhenguo Li, Liwei Wang

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This work is mostly theoretical, with no negative outcomes.
Researcher Affiliation Collaboration Kai Zheng1 zhengk92@gmail.com Tianle Cai2,3 caitianle1998@pku.edu.cn Weiran Huang4 weiran.huang@outlook.com Zhenguo Li4 li.zhenguo@huawei.com Liwei Wang5,6, wanglw@cis.pku.edu.cn 1 Kwai Inc. 2 School of Mathematical Sciences, Peking University 3 Haihua Institute for Frontier Information Technology 4 Huawei Noah s Ark Lab 5 Key Laboratory of Machine Perception, MOE, School of EECS, Peking University 6 Center for Data Science, Peking University
Pseudocode Yes Algorithm 1: One-Point Bandits Learning-LDP, Algorithm 2: Two-Point Feedback Private Bandit Convex Optimization via Black-box Reduction, Algorithm 3: Generalized Linear Bandits with LDP
Open Source Code No Appendix could be found in the full version [43].
Open Datasets No The paper focuses on theoretical analysis of algorithms and regret bounds, without specifying or using any publicly available datasets for empirical training.
Dataset Splits No The paper is theoretical and does not report on empirical experiments that would involve dataset splits for training, validation, or testing.
Hardware Specification No The paper does not provide any specific hardware details such as GPU models, CPU specifications, or cloud resources used for running experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with specific hyperparameters, training configurations, or system-level settings.