12 citations · 55 across the 11 of their papers we have counts for
4 papers · 1 filter
Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares
Gavin Brown, Jonathan Hayase, Samuel Hopkins +5
We present a sample- and time-efficient differentially private algorithm for ordinary least squares, with error that depends linearly on the dimension and is independent of the con…
Near Optimal Private and Robust Linear Regression
Xiyang Liu, Prateek Jain, Weihao Kong +2
We study the canonical statistical estimation problem of linear regression from i.i.d.~examples under -differential privacy when some response variables are ad…
DP-PCA: Statistically Optimal and Differentially Private PCA
Xiyang Liu, Weihao Kong, Prateek Jain +1
We study the canonical statistical task of computing the principal component from i.i.d.~data in dimensions under -differential privacy. Although extensive…
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:…