Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Optimal Rates for Robust Stochastic Convex Optimization
Changyu Gao, Andrew Lowy, Xingyu Zhou +1
Machine learning algorithms in high-dimensional settings are highly susceptible to the influence of even a small fraction of structured outliers, making robust optimization techniq…
cs.LG2024
Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses
Changyu Gao, Andrew Lowy, Xingyu Zhou +1
We revisit the problem of federated learning (FL) with private data from people who do not trust the server or other silos/clients. In this context, every silo (e.g. hospital) has…
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…