Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy
Gautam Kamath, Mahbod Majid, Ankur Moitra +2
We study learning a discrete distribution under person-level differential privacy in the batched setting. Given users, each contributing i.i.d. samples from an unknown dist…
cs.LG2024
Private Geometric Median
Mahdi Haghifam, Thomas Steinke, Jonathan Ullman
In this paper, we study differentially private (DP) algorithms for computing the geometric median (GM) of a dataset: Given points, in , the goal i…
cs.LG2024
How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization
Andrew Lowy, Jonathan Ullman, Stephen J. Wright
We provide a simple and flexible framework for designing differentially private algorithms to find approximate stationary points of non-convex loss functions. Our framework is base…