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 …

Mean estimation under differential privacy is a fundamental problem, but worst-case optimal
mechanisms do not offer meaningful utility guarantees in practice when the global sensitivity …

We revisit the problem of designing scalable protocols for private statistics and private
federated learning when each device holds its private data. Locally differentially private …

We provide an approximation algorithm for k-means clustering in the\emph {one-
round}(aka\emph {non-interactive}) local model of differential privacy (DP). Our algorithm …

We study federated learning (FL) with non-convex loss functions and data from people who
do not trust the server or other silos. In this setting, each silo (eg hospital) must protect the …

Modern machine learning models toward various tasks with omic data analysis give rise to
threats of privacy leakage of patients involved in those datasets. Here, we proposed a …

We propose a new family of label randomizers for training regression models under the
constraint of label differential privacy (DP). In particular, we leverage the trade-offs between …

Recently, it is shown that shuffling can amplify the central differential privacy guarantees of
data randomized with local differential privacy. Within this setup, a centralized, trusted …

Federated Learning (FL) enables multiple distributed clients to collaboratively train a model
with owned datasets. To avoid the potential privacy threat in FL, researchers propose the DP …

Bridging the advantages of differential privacy in both centralized model (ie, high accuracy)
and local model (ie, minimum trust), the shuffle privacy model has potential applications in …