Subsampling focuses on selecting a subsample that can efficiently sketch the information of
the original data in terms of statistical inference. It provides a powerful tool in big data …

Privacy and communication constraints are two major bottlenecks in federated learning (FL)
and analytics (FA). We study the optimal accuracy of mean and frequency estimation …

In recent years, privacy and security concerns in machine learning have promoted trusted
federated learning to the forefront of research. Differential privacy has emerged as the de …

Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a
wide range of general natural language processing (NLP) tasks. Researchers have …

Graph Neural Networks have achieved tremendous success in modeling complex graph
data in a variety of applications. However, there are limited studies investigating privacy …

We study the effect of the batch size to the total gradient variance in differentially private
stochastic gradient descent (DP-SGD), seeking a theoretical explanation for the usefulness …

Utilizing sensitive images (eg, human faces) for training DL models raises privacy concerns.
One straightforward solution is to replace the private images with synthetic ones generated …

Objectives Clinical trial data sharing is crucial for promoting transparency and collaborative
efforts in medical research. Differential privacy (DP) is a formal statistical technique for …

In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks by
conditioning on demonstrations of question-answer pairs and it has been shown to have …

We study a private variant of ADMM with (strongly) convex objective functions. We consider
a privacy model in which each iteration corresponds to a user whose private function is …