We study the problem of subsampling in differential privacy (DP), a question that is the
centerpiece behind many successful differentially private machine learning algorithms …

This paper studies federated learning (FL)--especially cross-silo FL--with data from people
who do not trust the server or other silos. In this setting, each silo (eg hospital) has data from …

We examine the robustness and privacy of Bayesian inference, under assumptions on the
prior, and with no modifications to the Bayesian framework. First, we generalise the concept …

We consider three different variants of differential privacy (DP), namely approximate DP,
Rényi DP (RDP), and hypothesis test DP. In the first part, we develop a machinery for …

Traditional differential privacy is independent of the data distribution. However, this is not
well-matched with the modern machine learning context, where models are trained on …

Because learning sometimes involves sensitive data, machine learning algorithms have
been extended to offer differential privacy for training data. In practice, this has been mostly …

Abstract Propose-Test-Release (PTR) is a differential privacy framework that works with
local sensitivity of functions, instead of their global sensitivity. This framework is typically …

Most works in learning with differential privacy (DP) have focused on the setting where each
user has a single sample. In this work, we consider the setting where each user holds $ m …

In this paper we prove that the sample complexity of properly learning a class of Littlestone
dimension d with approximate differential privacy is Õ (d 6), ignoring privacy and accuracy …

Federated learning (FL) is a common and practical framework for learning a machine model
in a decentralized fashion. A primary motivation behind this decentralized approach is data …