← Search

Gennady Samorodnitsky

3 accepted papers

2023

Adaptive Privacy Composition for Accuracy-first Mechanisms

NeurIPS 2023poster

Although there has been work to develop ex-post private mechanisms from Ligett et al. '17 and Whitehouse et al '22 that seeks to provide privacy guarantees subject to a target level of accuracy, there was not a way to use them in conjunction with differentially private mechanisms. Furthermore, ther…

Cited by 3SourcePDFScholar
2022

Minimax M-estimation under Adversarial Contamination

ICML 2022spotlight

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. We make minimal assumptions on the distribution of the uncontaminated random variables, namely, we only assume the existenc…

Cited by 8SourcePDFScholar
2022

Nearly Optimal Catoni’s M-estimator for Infinite Variance

ICML 2022spotlight

In this paper, we extend the remarkable M-estimator of Catoni \citep{Cat12} to situations where the variance is infinite. In particular, given a sequence of i.i.d random variables $\{X_i\}_{i=1}^n$ from distribution $\mathcal{D}$ over $\mathbb{R}$ with mean $\mu$, we only assume the existence of a k…

Cited by 17SourcePDFScholar