We provide an information-theoretic framework for studying the generalization properties of
machine learning algorithms. Our framework ties together existing approaches, including …

When two different parties use the same learning rule on their own data, how can we test
whether the distributions of the two outcomes are similar? In this paper, we study the …

Previous work on user-level differential privacy (DP)[Ghazi et al. NeurIPS 2021, Bun et al.
STOC 2023] obtained generic algorithms that work for various learning tasks. However, their …

We show that every approximately differentially private learning algorithm (possibly
improper) for a class H with Littlestone dimension d requires Ω (log*(d)) examples. As a …

We study the power of interactivity in local differential privacy. First, we focus on the
difference between fully interactive and sequentially interactive protocols. Sequentially …

We show that many definitions of stability found in the learning theory literature are
equivalent to one another. We distinguish between two families of definitions of stability …

Hypothesis testing plays a central role in statistical inference, and is used in many settings
where privacy concerns are paramount. This work answers a basic question about privately …

In this paper, we initiate a principled study of how the generalization properties of
approximate differential privacy can be used to perform adaptive hypothesis testing, while …

We study the space complexity of the two related fields of differential privacy and adaptive
data analysis. Specifically, Under standard cryptographic assumptions, we show that there …

In this paper, we aim to understand the generalization properties of generative adversarial
networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a …