Systems | Information | Learning | Optimization
 

SILO: Stable Estimators for Fast Private Statistics

Abstract:
We will discuss a new set of techniques for stable statistical estimation, leading to fast and near-optimal private algorithms for mean estimation, covariance estimation, and linear regression. The analysis proceeds by constructing a stabilizing wrapper around a greedy outlier-removal process. We will also discuss connections with a recent line of work on robustness and auditing.
Based on work with Sam Hopkins, Adam Smith, Jon Hayase, Xiyang Liu, Weihao Kong, Sewoong Oh, and Juan Perdomo.
Bio:
Gavin Brown is an Assistant Professor at the University of Wisconsin–Madison, in the Department of Computer Sciences. He was a postdoctoral scholar at the University of Washington, where he was supervised by Sewoong Oh. He received his PhD from Boston University, where he was advised by Adam Smith.

September 3, 2025
12:30 pm (1h)

Orchard View Room

Gavin Brown, UW-Madison

video