We investigate practical and scalable algorithms for training large language models (LLMs)
with user-level differential privacy (DP) in order to provably safeguard all the examples …

This paper studies federated linear contextual bandits under the notion of user-level
differential privacy (DP). We first introduce a unified federated bandits framework that can …

We study the problem of differentially private (DP) stochastic convex optimization (SCO)
under the notion of user-level differential privacy. In this problem, there are $ n $ users, each …

We study person-level differentially private (DP) mean estimation in the case where each
person holds multiple samples. DP here requires the usual notion of distributional stability …

ABSTRACT A distinguishing characteristic of federated learning is that the (local) client data
could have statistical heterogeneity. This heterogeneity has motivated the design of …

Most of the literature on differential privacy considers the item-level case where each user
has a single observation, but a growing field of interest is that of user-level privacy where …

The sampling problem under local differential privacy has recently been studied with
potential applications to generative models, but a fundamental analysis of its privacy-utility …

Previous studies yielded discouraging results for item-level locally differentially private linear
regression with $ s^* $-sparsity assumption, where the minimax rate for $ nm $ samples is …

We are currently facing a rapid growth of data contents originating from edge devices. These
data resources offer significant potential for learning and extracting complex patterns in a …

[Objective] This paper systematically introduces local differential privacy and provides a
reference for the protection of personal data privacy under data sharing and …