Federated linear contextual bandits with user-level differential privacy

R Huang, H Zhang, L Melis, M Shen… - International …, 2023 - proceedings.mlr.press
This paper studies federated linear contextual bandits under the notion of user-level
differential privacy (DP). We first introduce a unified federated bandits framework that can …

Locally differentially private (contextual) bandits learning

K Zheng, T Cai, W Huang, Z Li… - Advances in Neural …, 2020 - proceedings.neurips.cc
We study locally differentially private (LDP) bandits learning in this paper. First, we propose
simple black-box reduction frameworks that can solve a large family of context-free bandits …

When privacy meets partial information: A refined analysis of differentially private bandits

A Azize, D Basu - Advances in Neural Information …, 2022 - proceedings.neurips.cc
We study the problem of multi-armed bandits with ε-global Differential Privacy (DP). First, we
prove the minimax and problem-dependent regret lower bounds for stochastic and linear …

Local differential privacy for regret minimization in reinforcement learning

E Garcelon, V Perchet… - Advances in Neural …, 2021 - proceedings.neurips.cc
Reinforcement learning algorithms are widely used in domains where it is desirable to
provide a personalized service. In these domains it is common that user data contains …

Privacy-preserving q-learning with functional noise in continuous spaces

B Wang, N Hegde - Advances in Neural Information …, 2019 - proceedings.neurips.cc
We consider differentially private algorithms for reinforcement learning in continuous
spaces, such that neighboring reward functions are indistinguishable. This protects the …

Differentially private multi-armed bandits in the shuffle model

J Tenenbaum, H Kaplan, Y Mansour… - Advances in Neural …, 2021 - proceedings.neurips.cc
Abstract We give an $(\varepsilon,\delta) $-differentially private algorithm for the Multi-Armed
Bandit (MAB) problem in the shuffle model with a distribution-dependent regret of $ O\left …

Differentially private reinforcement learning with linear function approximation

X Zhou - Proceedings of the ACM on Measurement and Analysis …, 2022 - dl.acm.org
Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized
services, where users' sensitive and private information needs to be protected, we study …

On differentially private federated linear contextual bandits

X Zhou, SR Chowdhury - arXiv preprint arXiv:2302.13945, 2023 - arxiv.org
We consider cross-silo federated linear contextual bandit (LCB) problem under differential
privacy, where multiple silos (agents) interact with the local users and communicate via a …

Optimal rates of (locally) differentially private heavy-tailed multi-armed bandits

Y Tao, Y Wu, P Zhao, D Wang - International Conference on …, 2022 - proceedings.mlr.press
In this paper we investigate the problem of stochastic multi-armed bandits (MAB) in the
(local) differential privacy (DP/LDP) model. Unlike previous results that assume …

Shuffle private linear contextual bandits

SR Chowdhury, X Zhou - arXiv preprint arXiv:2202.05567, 2022 - arxiv.org
Differential privacy (DP) has been recently introduced to linear contextual bandits to formally
address the privacy concerns in its associated personalized services to participating users …