b'Gautam Kamath'

research

∙ 08/11/2023

Private Distribution Learning with Public Data: The View from Sample Compression

We study the problem of private distribution learning with access to pub...

0 Shai Ben-David, et al. ∙

research

∙ 03/07/2023

Exploring the Limits of Indiscriminate Data Poisoning Attacks

Indiscriminate data poisoning attacks aim to decrease a model's test acc...

0 Yiwei Lu, et al. ∙

research

∙ 03/02/2023

Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance

Differentially private stochastic gradient descent privatizes model trai...

0 Xin Gu, et al. ∙

research

∙ 02/06/2023

Private GANs, Revisited

We show that the canonical approach for training differentially private ...

0 Alex Bie, et al. ∙

research

∙ 01/30/2023

A Bias-Variance-Privacy Trilemma for Statistical Estimation

The canonical algorithm for differentially private mean estimation is to...

0 Gautam Kamath, et al. ∙

research

∙ 12/21/2022

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks

We introduce camouflaged data poisoning attacks, a new attack vector tha...

0 Jimmy Z. Di, et al. ∙

research

∙ 12/13/2022

Considerations for Differentially Private Learning with Large-Scale Public Pretraining

The performance of differentially private machine learning can be booste...

0 Florian Tramèr, et al. ∙

research

∙ 12/09/2022

Robustness Implies Privacy in Statistical Estimation

We study the relationship between adversarial robustness and differentia...

0 Samuel B. Hopkins, et al. ∙

research

∙ 08/16/2022

Private Estimation with Public Data

We initiate the study of differentially private (DP) estimation with acc...

0 Alex Bie, et al. ∙

research

∙ 06/06/2022

Per-Instance Privacy Accounting for Differentially Private Stochastic Gradient Descent

Differentially private stochastic gradient descent (DP-SGD) is the workh...

12 Da Yu, et al. ∙

research

∙ 05/17/2022

New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma

We prove new lower bounds for statistical estimation tasks under the con...

0 Gautam Kamath, et al. ∙

research

∙ 04/19/2022

Indiscriminate Data Poisoning Attacks on Neural Networks

Data poisoning attacks, in which a malicious adversary aims to influence...

0 Yiwei Lu, et al. ∙

research

∙ 01/27/2022

Calibration with Privacy in Peer Review

Reviewers in peer review are often miscalibrated: they may be strict, le...

0 Wenxin Ding, et al. ∙

research

∙ 11/25/2021

Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanism

We give the first polynomial-time algorithm to estimate the mean of a d-...

0 Samuel B. Hopkins, et al. ∙

research

∙ 11/09/2021

The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection

Hyperparameter optimization is a ubiquitous challenge in machine learnin...

0 Shubhankar Mohapatra, et al. ∙

research

∙ 11/08/2021

A Private and Computationally-Efficient Estimator for Unbounded Gaussians

We give the first polynomial-time, polynomial-sample, differentially pri...

0 Gautam Kamath, et al. ∙

research

∙ 10/27/2021

Unbiased Statistical Estimation and Valid Confidence Intervals Under Differential Privacy

We present a method for producing unbiased parameter estimates and valid...

0 Christian Covington, et al. ∙

research

∙ 10/13/2021

Differentially Private Fine-tuning of Language Models

We give simpler, sparser, and faster algorithms for differentially priva...

0 Da Yu, et al. ∙

research

∙ 06/02/2021

Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data

We study stochastic convex optimization with heavy-tailed data under the...

0 Gautam Kamath, et al. ∙

research

∙ 03/04/2021

Remember What You Want to Forget: Algorithms for Machine Unlearning

We study the problem of forgetting datapoints from a learnt model. In th...

5 Ayush Sekhari, et al. ∙

research

∙ 10/19/2020

On the Sample Complexity of Privately Learning Unbounded High-Dimensional Gaussians

We provide sample complexity upper bounds for agnostically learning mult...

0 Ishaq Aden-Ali, et al. ∙

research

∙ 10/18/2020

Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization

A common pain point in differentially private machine learning is the si...

13 Pranav Subramani, et al. ∙

research

∙ 06/11/2020

CoinPress: Practical Private Mean and Covariance Estimation

We present simple differentially private estimators for the mean and cov...

0 Sourav Biswas, et al. ∙

research

∙ 04/30/2020

A Primer on Private Statistics

Differentially private statistical estimation has seen a flurry of devel...

0 Gautam Kamath, et al. ∙

research

∙ 03/31/2020

The Discrete Gaussian for Differential Privacy

We show how to efficiently provide differentially private answers to cou...

4 Clement Canonne, et al. ∙

research

∙ 02/27/2020

PAPRIKA: Private Online False Discovery Rate Control

In hypothesis testing, a false discovery occurs when a hypothesis is inc...

0 Wanrong Zhang, et al. ∙

research

∙ 02/21/2020

Locally Private Hypothesis Selection

We initiate the study of hypothesis selection under local differential p...

0 Sivakanth Gopi, et al. ∙

research

∙ 02/21/2020

Private Mean Estimation of Heavy-Tailed Distributions

We give new upper and lower bounds on the minimax sample complexity of d...

0 Gautam Kamath, et al. ∙

research

∙ 02/21/2020

Privately Learning Markov Random Fields

We consider the problem of learning Markov Random Fields (including the ...

0 Huanyu Zhang, et al. ∙

research

∙ 11/17/2019

Random Restrictions of High-Dimensional Distributions and Uniformity Testing with Subcube Conditioning

We give a nearly-optimal algorithm for testing uniformity of distributio...

0 Clément L. Canonne, et al. ∙

research

∙ 09/09/2019

Differentially Private Algorithms for Learning Mixtures of Separated Gaussians

Learning the parameters of a Gaussian mixtures models is a fundamental a...

0 Gautam Kamath, et al. ∙

research

∙ 05/30/2019

Private Hypothesis Selection

We provide a differentially private algorithm for hypothesis selection. ...

0 Mark Bun, et al. ∙

research

∙ 05/28/2019

Private Identity Testing for High-Dimensional Distributions

In this work we present novel differentially private identity (goodness-...

0 Clément L. Canonne, et al. ∙

research

∙ 11/27/2018

The Structure of Optimal Private Tests for Simple Hypotheses

Hypothesis testing plays a central role in statistical inference, and is...

0 Clément L. Canonne, et al. ∙

research

∙ 07/17/2018

Anaconda: A Non-Adaptive Conditional Sampling Algorithm for Distribution Testing

We investigate distribution testing with access to non-adaptive conditio...

0 Gautam Kamath, et al. ∙

research

∙ 05/01/2018

Privately Learning High-Dimensional Distributions

We design nearly optimal differentially private algorithms for learning ...

0 Gautam Kamath, et al. ∙

research

∙ 03/07/2018

Sever: A Robust Meta-Algorithm for Stochastic Optimization

In high dimensions, most machine learning methods are brittle to even a ...

0 Ilias Diakonikolas, et al. ∙

research

∙ 02/28/2018

INSPECTRE: Privately Estimating the Unseen

We develop differentially private methods for estimating various distrib...

0 Jayadev Acharya, et al. ∙

research

∙ 02/20/2018

Actively Avoiding Nonsense in Generative Models

A generative model may generate utter nonsense when it is fit to maximiz...

0 Steve Hanneke, et al. ∙

research

∙ 10/11/2017

Concentration of Multilinear Functions of the Ising Model with Applications to Network Data

We prove near-tight concentration of measure for polynomial functions of...

0 Constantinos Daskalakis, et al. ∙

research

∙ 04/12/2017

Robustly Learning a Gaussian: Getting Optimal Error, Efficiently

We study the fundamental problem of learning the parameters of a high-di...

0 Ilias Diakonikolas, et al. ∙

research

∙ 03/02/2017

Being Robust (in High Dimensions) Can Be Practical

Robust estimation is much more challenging in high dimensions than it is...

0 Ilias Diakonikolas, et al. ∙

research

∙ 04/21/2016

Robust Estimators in High Dimensions without the Computational Intractability

We study high-dimensional distribution learning in an agnostic setting w...

0 Ilias Diakonikolas, et al. ∙

Gautam Kamath

Featured Co-authors