On robustness and local differential privacy Page 1 The Annals of Statistics 2023, Vol. 51, No.
2, 717–737 https://doi.org/10.1214/23-AOS2267 © Institute of Mathematical Statistics, 2023 …

We examine the relationship between learnability and robust learnability for the problem of
distribution learning. We show that learnability implies robust learnability if the adversary …

We study the problem of robustly estimating the parameter $ p $ of an Erdős-Rényi random
graph on $ n $ nodes, where a $\gamma $ fraction of nodes may be adversarially corrupted …

We present a new finite-sample analysis of Catoni's M-estimator under adversarial
contamination, where an adversary is allowed to corrupt a fraction of the samples arbitrarily …

The last decade has seen a number of advances in computationally efficient algorithms for
statistical methods subject to robustness constraints. An estimator may be robust in a …

This paper studies the construction of adaptive confidence intervals under Huber's
contamination model when the contamination proportion is unknown. For the robust …

Approximating distributions from their samples is a canonical statistical-learning problem.
One of its most powerful and successful modalities approximates every distribution to an …

Modern applications, including natural language processing, sensor networks, collaborative
filtering, and federated learning, necessitate data collection from diverse sources. However …

Machine learning and statistical algorithms are now implemented at a large scale in almost
every aspect of our society, significantly impacting our daily lives through their performance …

The fundamental theorem of statistical learning establishes the equivalence between
various notions of both agnostic and realizable Probably Approximately Correct (PAC) …