b'Kunal Talwar'

research

∙ 07/28/2023

Mean Estimation with User-level Privacy under Data Heterogeneity

A key challenge in many modern data analysis tasks is that user data are...

0 Rachel Cummings, et al. ∙

research

∙ 07/27/2023

Samplable Anonymous Aggregation for Private Federated Data Analysis

We revisit the problem of designing scalable protocols for private stati...

0 Kunal Talwar, et al. ∙

research

∙ 07/21/2023

Differentially Private Heavy Hitter Detection using Federated Analytics

In this work, we study practical heuristics to improve the performance o...

0 Karan Chadha, et al. ∙

research

∙ 06/07/2023

Fast Optimal Locally Private Mean Estimation via Random Projections

We study the problem of locally private mean estimation of high-dimensio...

0 Hilal Asi, et al. ∙

research

∙ 02/27/2023

Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime

We consider online learning problems in the realizable setting, where th...

0 Hilal Asi, et al. ∙

research

∙ 12/24/2022

Concentration of the Langevin Algorithm's Stationary Distribution

A canonical algorithm for log-concave sampling is the Langevin Algorithm...

0 Jason M. Altschuler, et al. ∙

research

∙ 11/18/2022

Private Federated Statistics in an Interactive Setting

Privately learning statistics of events on devices can enable improved u...

0 Audra McMillan, et al. ∙

research

∙ 10/24/2022

Private Online Prediction from Experts: Separations and Faster Rates

Online prediction from experts is a fundamental problem in machine learn...

0 Hilal Asi, et al. ∙

research

∙ 10/24/2022

Subspace Recovery from Heterogeneous Data with Non-isotropic Noise

Recovering linear subspaces from data is a fundamental and important tas...

0 John Duchi, et al. ∙

research

∙ 10/16/2022

Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling

Sampling from a high-dimensional distribution is a fundamental task in s...

0 Jason M. Altschuler, et al. ∙

research

∙ 08/09/2022

Stronger Privacy Amplification by Shuffling for Rényi and Approximate Differential Privacy

The shuffle model of differential privacy has gained significant interes...

0 Vitaly Feldman, et al. ∙

research

∙ 07/18/2022

FLAIR: Federated Learning Annotated Image Repository

Cross-device federated learning is an emerging machine learning (ML) par...

0 Congzheng Song, et al. ∙

research

∙ 05/27/2022

Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss

A central issue in machine learning is how to train models on sensitive ...

0 Jason M. Altschuler, et al. ∙

research

∙ 05/05/2022

Optimal Algorithms for Mean Estimation under Local Differential Privacy

We study the problem of mean estimation of ℓ_2-bounded vectors under the...

0 Hilal Asi, et al. ∙

research

∙ 03/01/2022

Private Frequency Estimation via Projective Geometry

In this work, we propose a new algorithm ProjectiveGeometryResponse (PGR...

0 Vitaly Feldman, et al. ∙

research

∙ 02/22/2022

Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation

Computing the noisy sum of real-valued vectors is an important primitive...

0 Kunal Talwar, et al. ∙

research

∙ 06/25/2021

Private Adaptive Gradient Methods for Convex Optimization

We study adaptive methods for differentially private convex optimization...

0 Hilal Asi, et al. ∙

research

∙ 03/02/2021

Private Stochastic Convex Optimization: Optimal Rates in ℓ_1 Geometry

Stochastic convex optimization over an ℓ_1-bounded domain is ubiquitous ...

0 Hilal Asi, et al. ∙

research

∙ 02/24/2021

Lossless Compression of Efficient Private Local Randomizers

Locally Differentially Private (LDP) Reports are commonly used for colle...

0 Vitaly Feldman, et al. ∙

research

∙ 12/23/2020

Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling

Recent work of Erlingsson, Feldman, Mironov, Raghunathan, Talwar, and Th...

0 Vitaly Feldman, et al. ∙

research

∙ 12/11/2020

When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?

Modern machine learning models are complex and frequently encode surpris...

18 Gavin Brown, et al. ∙

research

∙ 12/02/2020

On the Error Resistance of Hinge Loss Minimization

Commonly used classification algorithms in machine learning, such as sup...

0 Kunal Talwar, et al. ∙

research

∙ 10/27/2020

Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC

Various differentially private algorithms instantiate the exponential me...

0 Arun Ganesh, et al. ∙

research

∙ 10/26/2020

Stochastic Optimization with Laggard Data Pipelines

State-of-the-art optimization is steadily shifting towards massively par...

20 Naman Agarwal, et al. ∙

research

∙ 06/12/2020

Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses

Uniform stability is a notion of algorithmic stability that bounds the w...

0 Raef Bassily, et al. ∙

research

∙ 05/10/2020

Private Stochastic Convex Optimization: Optimal Rates in Linear Time

We study differentially private (DP) algorithms for stochastic convex op...

38 Vitaly Feldman, et al. ∙

research

∙ 02/08/2020

Exploring the Memorization-Generalization Continuum in Deep Learning

Human learners appreciate that some facts demand memorization whereas ot...

9 Ziheng Jiang, et al. ∙

research

∙ 11/05/2019

Computational Separations between Sampling and Optimization

Two commonly arising computational tasks in Bayesian learning are Optimi...

0 Kunal Talwar, et al. ∙

research

∙ 08/28/2019

Rényi Differential Privacy of the Sampled Gaussian Mechanism

The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and ...

0 Ilya Mironov, et al. ∙

research

∙ 08/27/2019

Private Stochastic Convex Optimization with Optimal Rates

We study differentially private (DP) algorithms for stochastic convex op...

9 Raef Bassily, et al. ∙

research

∙ 04/23/2019

Semi-Cyclic Stochastic Gradient Descent

We consider convex SGD updates with a block-cyclic structure, i.e. where...

0 Hubert Eichner, et al. ∙

research

∙ 02/22/2019

Better Algorithms for Stochastic Bandits with Adversarial Corruptions

We study the stochastic multi-armed bandits problem in the presence of a...

0 Anupam Gupta, et al. ∙

research

∙ 11/29/2018

Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity

Sensitive statistics are often collected across sets of users, with repe...

4 Úlfar Erlingsson, et al. ∙

research

∙ 11/19/2018

Private Selection from Private Candidates

Differentially Private algorithms often need to select the best amongst ...

0 Jingcheng Liu, et al. ∙

research

∙ 08/20/2018

Privacy Amplification by Iteration

Many commonly used learning algorithms work by iteratively updating an i...

0 Vitaly Feldman, et al. ∙

research

∙ 06/19/2018

Online Linear Quadratic Control

We study the problem of controlling linear time-invariant systems with k...

0 Alon Cohen, et al. ∙

research

∙ 04/30/2018

Adversarially Robust Generalization Requires More Data

Machine learning models are often susceptible to adversarial perturbatio...

0 Ludwig Schmidt, et al. ∙

research

∙ 03/05/2018

Online learning over a finite action set with limited switching

This paper studies the value of switching actions in the Prediction From...

0 Jason Altschuler, et al. ∙

research

∙ 02/24/2018

Scalable Private Learning with PATE

The rapid adoption of machine learning has increased concerns about the ...

0 Nicolas Papernot, et al. ∙

research

∙ 08/26/2017

On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches

The recent, remarkable growth of machine learning has led to intense int...

0 Martín Abadi, et al. ∙

research

∙ 10/18/2016

Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data

Some machine learning applications involve training data that is sensiti...

0 Nicolas Papernot, et al. ∙

research

∙ 07/01/2016

Deep Learning with Differential Privacy

Machine learning techniques based on neural networks are achieving remar...

0 Martín Abadi, et al. ∙

research

∙ 03/14/2016

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

TensorFlow is an interface for expressing machine learning algorithms, a...

0 Martín Abadi, et al. ∙

research

∙ 11/20/2014

Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry

Empirical Risk Minimization (ERM) is a standard technique in machine lea...

0 Kunal Talwar, et al. ∙

Kunal Talwar

Featured Co-authors