259 citations · 1.6k across the 62 of their papers we have counts for
5 papers · 1 filter
Differential privacy and robust statistics in high dimensions
Xiyang Liu, Weihao Kong, Sewoong Oh
We introduce a universal framework for characterizing the statistical efficiency of a statistical estimation problem with differential privacy guarantees. Our framework, which we c…
Gradient flows on graphons: existence, convergence, continuity equations
Sewoong Oh, Soumik Pal, Raghav Somani +1
Wasserstein gradient flows on probability measures have found a host of applications in various optimization problems. They typically arise as the continuum limit of exchangeable p…
Gradient Inversion with Generative Image Prior
Jinwoo Jeon, Jaechang Kim, Kangwook Lee +2
Federated Learning (FL) is a distributed learning framework, in which the local data never leaves clients devices to preserve privacy, and the server trains models on the data via…
Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals
Lang Liu, Krishna Pillutla, Sean Welleck +3
The spectacular success of deep generative models calls for quantitative tools to measure their statistical performance. Divergence frontiers have recently been proposed as an eval…
Robust and Differentially Private Mean Estimation
Xiyang Liu, Weihao Kong, Sham Kakade +1
In statistical learning and analysis from shared data, which is increasingly widely adopted in platforms such as federated learning and meta-learning, there are two major concerns:…