activity
20152022
most citedNear-Optimal Offline Reinforcement Learning via Double Variance Reduction

18 citations · 55 across the 14 of their papers we have counts for

collaborators

34 papers

cs.LG2022

Towards Differential Relational Privacy and its use in Question Answering

Simone Bombari, Alessandro Achille, Zijian Wang +6

Memorization of the relation between entities in a dataset can lead to privacy issues when using a trained model for question answering. We introduce Relational Memorization (RM) t…

cs.LG20223 cited

Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE

Yuqing Zhu, Yu-Xiang Wang

We provide an end-to-end Renyi DP based-framework for differentially private top- selection. Unlike previous approaches, which require a data-independent choice on , we propo…

cs.CV2022

Mixed Differential Privacy in Computer Vision

Aditya Golatkar, Alessandro Achille, Yu-Xiang Wang +3

We introduce AdaMix, an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data. While pre-training language…

cs.LG20223 cited

Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism

Ming Yin, Yaqi Duan, Mengdi Wang +1

Offline reinforcement learning, which seeks to utilize offline/historical data to optimize sequential decision-making strategies, has gained surging prominence in recent studies. D…

cs.LG20224 cited

Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond

Dheeraj Baby, Yu-Xiang Wang

We study the framework of universal dynamic regret minimization with strongly convex losses. We answer an open problem in Baby and Wang 2021 by showing that in a proper learning se…

cs.CR20213 cited

Privately Publishable Per-instance Privacy

Rachel Redberg, Yu-Xiang Wang

We consider how to privately share the personalized privacy losses incurred by objective perturbation, using per-instance differential privacy (pDP). Standard differential privacy…