activity
20212024
most citedOn Differentially Private Federated Linear Contextual Bandits

3 citations · 8 across the 9 of their papers we have counts for

collaborators

8 papers

cs.LG2023

Differentially Private Reward Estimation with Preference Feedback

Sayak Ray Chowdhury, Xingyu Zhou, Nagarajan Natarajan

Learning from preference-based feedback has recently gained considerable traction as a promising approach to align generative models with human interests. Instead of relying on num…

cs.LG2023

Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards

Yulian Wu, Xingyu Zhou, Sayak Ray Chowdhury +1

In this paper, we study the problem of (finite horizon tabular) Markov decision processes (MDPs) with heavy-tailed rewards under the constraint of differential privacy (DP). Compar…

cs.LG20233 cited

Provably Efficient Model-Free Algorithms for Non-stationary CMDPs

Honghao Wei, Arnob Ghosh, Ness Shroff +2

We study model-free reinforcement learning (RL) algorithms in episodic non-stationary constrained Markov Decision Processes (CMDPs), in which an agent aims to maximize the expected…

cs.LG20233 cited

On Differentially Private Federated Linear Contextual Bandits

Xingyu Zhou, Sayak Ray Chowdhury

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…

cs.LG2022

Differentially Private Reinforcement Learning with Linear Function Approximation

Xingyu Zhou

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 re…

cs.CV2022

Adversarial Attack via Dual-Stage Network Erosion

Yexin Duan, Junhua Zou, Xingyu Zhou +3

Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations. Although existing attacks have achieved promising results, i…