5 citations · 6 across the 14 of their papers we have counts for
17 papers
Understanding Private Evolution as Learning-Augmented Clustering
Audra McMillan, Kunal Talwar, Felix Zhou
Private Evolution (PE) is a differentially private algorithm for synthetic data generation. While it can be viewed as a Wasserstein learning algorithm, it performs much better in p…
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…
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…
Faster Rates for Private Adversarial Bandits
Hilal Asi, Vinod Raman, Kunal Talwar
We design new differentially private algorithms for the problems of adversarial bandits and bandits with expert advice. For adversarial bandits, we give a simple and efficient conv…
On Privately Estimating a Single Parameter
Hilal Asi, John C. Duchi, Kunal Talwar
We investigate differentially private estimators for individual parameters within larger parametric models. While generic private estimators exist, the estimators we provide repose…
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…
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…
Fingerprinting Codes Meet Geometry: Improved Lower Bounds for Private Query Release and Adaptive Data Analysis
Xin Lyu, Kunal Talwar
Fingerprinting codes are a crucial tool for proving lower bounds in differential privacy. They have been used to prove tight lower bounds for several fundamental questions, especia…
Privacy-Computation trade-offs in Private Repetition and Metaselection
Kunal Talwar
A Private Repetition algorithm takes as input a differentially private algorithm with constant success probability and boosts it to one that succeeds with high probability. These a…
Adaptive Batch Size for Privately Finding Second-Order Stationary Points
Daogao Liu, Kunal Talwar
There is a gap between finding a first-order stationary point (FOSP) and a second-order stationary point (SOSP) under differential privacy constraints, and it remains unclear wheth…
Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization
Guy Kornowski, Daogao Liu, Kunal Talwar
We study differentially private (DP) optimization algorithms for stochastic and empirical objectives which are neither smooth nor convex, and propose methods that return a Goldstei…
Instance-Optimal Private Density Estimation in the Wasserstein Distance
Vitaly Feldman, Audra McMillan, Satchit Sivakumar +1
Estimating the density of a distribution from samples is a fundamental problem in statistics. In many practical settings, the Wasserstein distance is an appropriate error metric fo…
Wally: Batched Private Nearest Neighbor Search at Scale
Hilal Asi, Fabian Boemer, Nicholas Genise +8
We present Wally, a batched private nearest-neighbor search protocol that uses differential privacy to break the linear computation barrier of fully-oblivious schemes. In Tiptoe, t…
Private Online Learning via Lazy Algorithms
Hilal Asi, Tomer Koren, Daogao Liu +1
We study the problem of private online learning, specifically, online prediction from experts (OPE) and online convex optimization (OCO). We propose a new transformation that trans…
Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages
Hilal Asi, Vitaly Feldman, Jelani Nelson +3
We study the problem of private vector mean estimation in the shuffle model of privacy where users each have a unit vector . We propose a new multi-mes…
PINE: Efficient Norm-Bound Verification for Secret-Shared Vectors
Guy N. Rothblum, Eran Omri, Junye Chen +1
Secure aggregation of high-dimensional vectors is a fundamental primitive in federated statistics and learning. A two-server system such as PRIO allows for scalable aggregation of…
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…