62 citations · 77 across the 7 of their papers we have counts for
7 papers
DP-Auditorium: a Large Scale Library for Auditing Differential Privacy
William Kong, Andrés Muñoz Medina, Mónica Ribero +1
New regulations and increased awareness of data privacy have led to the deployment of new and more efficient differentially private mechanisms across public institutions and indust…
Easy Differentially Private Linear Regression
Kareem Amin, Matthew Joseph, Mónica Ribero +1
Linear regression is a fundamental tool for statistical analysis. This has motivated the development of linear regression methods that also satisfy differential privacy and thus gu…
Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints
Monica Ribero, Haris Vikalo, Gustavo De Veciana
Federated learning systems facilitate training of global models in settings where potentially heterogeneous data is distributed across a large number of clients. Such systems opera…
A Joint Exponential Mechanism For Differentially Private Top-
Jennifer Gillenwater, Matthew Joseph, Andrés Muñoz Medina +1
We present a differentially private algorithm for releasing the sequence of elements with the highest counts from a data domain of elements. The algorithm is a "joint" inst…
Fast Dimension Independent Private AdaGrad on Publicly Estimated Subspaces
Peter Kairouz, Mónica Ribero, Keith Rush +1
We revisit the problem of empirical risk minimziation (ERM) with differential privacy. We show that noisy AdaGrad, given appropriate knowledge and conditions on the subspace from w…
Communication-Efficient Federated Learning via Optimal Client Sampling
Monica Ribero, Haris Vikalo
Federated learning (FL) ameliorates privacy concerns in settings where a central server coordinates learning from data distributed across many clients. The clients train locally an…
Federating Recommendations Using Differentially Private Prototypes
Mónica Ribero, Jette Henderson, Sinead Williamson +1
Machine learning methods allow us to make recommendations to users in applications across fields including entertainment, dating, and commerce, by exploiting similarities in users'…