Peter Kairouz

is this you? claim profile

0 followers
Google ∙ Stanford University

Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Trade-offs

We consider a distributed empirical risk minimization (ERM) optimization...
08/17/2020 ∙ by Antonious M. Girgis, et al. ∙ 21 ∙ share

read it
Dimension Independence in Unconstrained Private ERM via Adaptive Preconditioning

In this paper we revisit the problem of private empirical risk minimziat...
08/14/2020 ∙ by Peter Kairouz, et al. ∙ 0 ∙ share

read it
Breaking the Communication-Privacy-Accuracy Trilemma

Two major challenges in distributed learning and estimation are 1) prese...
07/22/2020 ∙ by Wei-Ning Chen, et al. ∙ 0 ∙ share

read it
Privacy Amplification via Random Check-Ins

Differentially Private Stochastic Gradient Descent (DP-SGD) forms a fund...
07/13/2020 ∙ by Borja Balle, et al. ∙ 12 ∙ share

read it
DP-CGAN: Differentially Private Synthetic Data and Label Generation

Generative Adversarial Networks (GANs) are one of the well-known models ...
01/27/2020 ∙ by Reihaneh Torkzadehmahani, et al. ∙ 0 ∙ share

read it
Advances and Open Problems in Federated Learning

Federated learning (FL) is a machine learning setting where many clients...
12/10/2019 ∙ by Peter Kairouz, et al. ∙ 32 ∙ share

read it
Can You Really Backdoor Federated Learning?

The decentralized nature of federated learning makes detecting and defen...
11/18/2019 ∙ by Ziteng Sun, et al. ∙ 0 ∙ share

read it
Generative Models for Effective ML on Private, Decentralized Datasets

To improve real-world applications of machine learning, experienced mode...
11/15/2019 ∙ by Sean Augenstein, et al. ∙ 29 ∙ share

read it
Theoretical Guarantees for Model Auditing with Finite Adversaries

Privacy concerns have led to the development of privacy-preserving appro...
11/08/2019 ∙ by Mario Diaz, et al. ∙ 0 ∙ share

read it
Context-Aware Local Differential Privacy

Local differential privacy (LDP) is a strong notion of privacy for indiv...
10/31/2019 ∙ by Jayadev Acharya, et al. ∙ 0 ∙ share

read it
Learning Generative Adversarial RePresentations (GAP) under Fairness and Censoring Constraints

We present Generative Adversarial rePresentations (GAP) as a data-driven...
09/27/2019 ∙ by Jiachun Liao, et al. ∙ 0 ∙ share

read it
A Tunable Loss Function for Classification

Recently, a parametrized class of loss functions called α-loss, α∈ [1,∞]...
06/05/2019 ∙ by Tyler Sypherd, et al. ∙ 0 ∙ share

read it
Federated Heavy Hitters Discovery with Differential Privacy

The discovery of heavy hitters (most frequent items) in user-generated d...
02/22/2019 ∙ by Wennan Zhu, et al. ∙ 0 ∙ share

read it
A Tunable Loss Function for Binary Classification

We present α-loss, α∈ [1,∞], a tunable loss function for binary classifi...
02/12/2019 ∙ by Tyler Sypherd, et al. ∙ 0 ∙ share

read it
Understanding Compressive Adversarial Privacy

Designing a data sharing mechanism without sacrificing too much privacy ...
09/21/2018 ∙ by Xiao Chen, et al. ∙ 0 ∙ share

read it
On the Optimality of the Kautz-Singleton Construction in Probabilistic Group Testing

We consider the probabilistic group testing problem where d random defec...
08/04/2018 ∙ by Huseyin A. Inan, et al. ∙ 0 ∙ share

read it
Generative Adversarial Privacy

We present a data-driven framework called generative adversarial privacy...
07/13/2018 ∙ by Chong Huang, et al. ∙ 0 ∙ share

read it
Siamese Generative Adversarial Privatizer for Biometric Data

State-of-the-art machine learning algorithms can be fooled by carefully ...
04/23/2018 ∙ by Witold Oleszkiewicz, et al. ∙ 0 ∙ share

read it
On the Contractivity of Privacy Mechanisms

We present a novel way to compare the statistical cost of privacy mechan...
01/18/2018 ∙ by Mario Diaz, et al. ∙ 0 ∙ share

read it
Context-Aware Generative Adversarial Privacy

Preserving the utility of published datasets while simultaneously provid...
10/26/2017 ∙ by Chong Huang, et al. ∙ 0 ∙ share

read it
Discrete Distribution Estimation under Local Privacy

The collection and analysis of user data drives improvements in the app ...
02/24/2016 ∙ by Peter Kairouz, et al. ∙ 0 ∙ share

read it

Peter Kairouz

Featured Co-authors

Yang Liu

Wei Li

Mehdi Bennis

Dawn Song

Qiang Yang

Martin Jaggi

Ramesh Raskar

Prateek Mittal

Mehryar Mohri

Xiao Chen

Tomasz Trzciński

Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Trade-offs

Dimension Independence in Unconstrained Private ERM via Adaptive Preconditioning

Breaking the Communication-Privacy-Accuracy Trilemma

Privacy Amplification via Random Check-Ins

DP-CGAN: Differentially Private Synthetic Data and Label Generation

Advances and Open Problems in Federated Learning

Can You Really Backdoor Federated Learning?

Generative Models for Effective ML on Private, Decentralized Datasets

Theoretical Guarantees for Model Auditing with Finite Adversaries

Context-Aware Local Differential Privacy

Learning Generative Adversarial RePresentations (GAP) under Fairness and Censoring Constraints

A Tunable Loss Function for Classification

Federated Heavy Hitters Discovery with Differential Privacy

A Tunable Loss Function for Binary Classification

Understanding Compressive Adversarial Privacy

On the Optimality of the Kautz-Singleton Construction in Probabilistic Group Testing

Generative Adversarial Privacy

Siamese Generative Adversarial Privatizer for Biometric Data

On the Contractivity of Privacy Mechanisms

Context-Aware Generative Adversarial Privacy

Discrete Distribution Estimation under Local Privacy