activity
20242026
collaborators

5 papers

cs.LG2026

Near-Optimal Pure Machine Unlearning for Smooth Strongly Convex Losses

Matthew Regehr, Gautam Kamath, Andrew Lowy

Machine unlearning is motivated by legal and user-facing requirements to remove the influence of individuals' data from trained models, such as the right to be forgotten. Prior wor…

cs.CR2026

Privacy Filters are Captured by Residues: A Characterization of Free Natural Filters and the Cost of Adaptivity

Matthew Regehr, Bingshan Hu, Ethan Leeman +3

We study privacy filters, which enable privacy accounting for differentially private (DP) mechanisms with adaptively chosen privacy characteristics. We develop a general theory tha…

cs.DS2026

Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph

Gautam Kamath, Alireza F. Pour, Matthew Regehr +1

We propose an algorithm with improved query-complexity for the problem of hypothesis selection under local differential privacy constraints. Given a set of probability distribu…

cs.CR2025

Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition

Christian Janos Lebeda, Matthew Regehr, Gautam Kamath +1

We consider the problem of computing tight privacy guarantees for the composition of subsampled differentially private mechanisms. Recent algorithms can numerically compute the pri…

math.ST2024

A Bias-Accuracy-Privacy Trilemma for Statistical Estimation

Gautam Kamath, Argyris Mouzakis, Matthew Regehr +3

Differential privacy (DP) is a rigorous notion of data privacy, used for private statistics. The canonical algorithm for differentially private mean estimation is to first clip the…