3 papers
cs.LG2022
On Private Online Convex Optimization: Optimal Algorithms in -Geometry and High Dimensional Contextual Bandits
Yuxuan Han, Zhicong Liang, Zhipeng Liang +3
Differentially private (DP) stochastic convex optimization (SCO) is ubiquitous in trustworthy machine learning algorithm design. This paper studies the DP-SCO problem with streamin…
cs.LG2021
Generalization Bounds for Stochastic Gradient Langevin Dynamics: A Unified View via Information Leakage Analysis
Bingzhe Wu, Zhicong Liang, Yatao Bian +3
Recently, generalization bounds of the non-convex empirical risk minimization paradigm using Stochastic Gradient Langevin Dynamics (SGLD) have been extensively studied. Several the…
cs.LG2020
Differentially Private Federated Learning with Laplacian Smoothing
Zhicong Liang, Bao Wang, Quanquan Gu +2
Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. However, an adversary may still be able to infer the p…