collaborators

7 papers

cs.LG2026

Efficient privacy loss accounting for subsampling and random allocation

Vitaly Feldman, Moshe Shenfeld

We consider the privacy amplification properties of a sampling scheme in which a user's data isused in steps chosen randomly and uniformly from a sequence (or set) of steps…

cs.LG2026

The Fast Mixing Mechanism for Differential Privacy

Omri Lev, Moshe Shenfeld, Vishwak Srinivasan +2

Randomized sketching is a central tool for compressing large-scale optimization problems while preserving accuracy. In particular, sketches that are based on structured matrices, s…

cs.LG2026

Near-Optimal Private Linear Regression via Iterative Hessian Mixing

Omri Lev, Moshe Shenfeld, Vishwak Srinivasan +2

We study differentially private ordinary least squares (DP-OLS) with bounded data via sketching-based mechanisms. While Gaussian sketching approaches have been explored for…

cs.CR2026

Differentially Private Nonparametric Confidence Intervals Under Minimal Distributional Assumptions

Tomer Shoham, Moshe Shenfeld, Noa Velner-Harris +1

We consider the problem of constructing differentially private nonparametric confidence intervals (CIs) for an arbitrary quantity using resampling. A growing body of work has adapt…

cs.LG2026

How Well Can Differential Privacy Be Audited in One Run?

Amit Keinan, Moshe Shenfeld, Katrina Ligett

Recent methods for auditing the privacy of machine learning algorithms have improved computational efficiency by simultaneously intervening on multiple training examples in a singl…

cs.LG2026

Privacy amplification by random allocation

Vitaly Feldman, Moshe Shenfeld

We consider the privacy amplification properties of a sampling scheme in which a user's data is used in k steps chosen randomly and uniformly from a sequence (or set) of t steps. T…