collaborators

6 papers

cs.CL2026

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts

Jiayuan Ye, Vitaly Feldman, Kunal Talwar

Large language models (LLMs) can struggle to memorize factual knowledge in their parameters, often leading to hallucinations and poor performance on knowledge-intensive tasks. In t…

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…

cs.LG2025

Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers and Gradient Clipping

Martin Pelikan, Sheikh Shams Azam, Vitaly Feldman +4

While federated learning (FL) and differential privacy (DP) have been extensively studied, their application to automatic speech recognition (ASR) remains largely unexplored due to…

cs.CR2025

PREAMBLE: Private and Efficient Aggregation via Block Sparse Vectors

Hilal Asi, Vitaly Feldman, Hannah Keller +2

We revisit the problem of secure aggregation of high-dimensional vectors in a two-server system such as Prio. These systems are typically used to aggregate vectors such as gradient…

stat.ML2025

Instance-Optimality for Private KL Distribution Estimation

Jiayuan Ye, Vitaly Feldman, Kunal Talwar

We study the fundamental problem of estimating an unknown discrete distribution over symbols, given i.i.d. samples from the distribution. We are interested in minimizin…

cs.CR2025

Local Pan-Privacy for Federated Analytics

Vitaly Feldman, Audra McMillan, Guy N. Rothblum +1

Pan-privacy was proposed by Dwork et al. as an approach to designing a private analytics system that retains its privacy properties in the face of intrusions that expose the system…