163 citations · 249 across the 22 of their papers we have counts for
4 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…
Fisher-Pitman permutation tests based on nonparametric Poisson mixtures with application to single cell genomics
Zhen Miao, Weihao Kong, Ramya Korlakai Vinayak +2
This paper investigates the theoretical and empirical performance of Fisher-Pitman-type permutation tests for assessing the equality of unknown Poisson mixture distributions. Build…
SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics
Jonathan Hayase, Weihao Kong, Raghav Somani +1
Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is w…
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:…