English
Related papers

Related papers: On the Sample Complexity of Privately Learning Unb…

200 papers

This paper investigates the approximation of Gaussian random variables in Banach spaces, focusing on the high-probability bounds for the approximation of Gaussian random variables using finitely many observations. We derive non-asymptotic…

Statistics Theory · Mathematics 2025-08-28 Daniel Winkle , Ingo Steinwart , Bernard Haasdonk

There has been a recent wave of interest in intermediate trust models for differential privacy that eliminate the need for a fully trusted central data collector, but overcome the limitations of local differential privacy. This interest has…

Data Structures and Algorithms · Computer Science 2020-12-07 Albert Cheu , Jonathan Ullman

The paper contains results in three areas: First we present a general estimate for tail probabilities of Gaussian quadratic forms with known expectation and variance. Thereafter we analyze the distribution of norms of complex Gaussian…

Probability · Mathematics 2019-03-20 Georg Berschneider , Björn Böttcher

We present simple differentially private estimators for the mean and covariance of multivariate sub-Gaussian data that are accurate at small sample sizes. We demonstrate the effectiveness of our algorithms both theoretically and empirically…

Machine Learning · Statistics 2026-02-10 Sourav Biswas , Yihe Dong , Gautam Kamath , Jonathan Ullman

A private learner is an algorithm that given a sample of labeled individual examples outputs a generalizing hypothesis while preserving the privacy of each individual. In 2008, Kasiviswanathan et al. (FOCS 2008) gave a generic construction…

Machine Learning · Computer Science 2015-07-03 Amos Beimel , Kobbi Nissim , Uri Stemmer

We consider the privacy amplification properties of a sampling scheme in which a user's data is used in k steps chosen randomly and uniformly from a sequence (or set) of t steps. This sampling scheme has been recently applied in the context…

Machine Learning · Computer Science 2026-01-16 Vitaly Feldman , Moshe Shenfeld

Gaussian Process Regression is a popular nonparametric regression method based on Bayesian principles that provides uncertainty estimates for its predictions. However, these estimates are of a Bayesian nature, whereas for some important…

Machine Learning · Computer Science 2023-08-09 Christian Fiedler , Carsten W. Scherer , Sebastian Trimpe

Bootstrap is a common tool for quantifying uncertainty in data analysis. However, besides additional computational costs in the application of the bootstrap on massive data, a challenging problem in bootstrap based inference under…

Machine Learning · Statistics 2025-05-05 Holger Dette , Carina Graw

We consider the problem of identifying the parameters of an unknown mixture of two arbitrary $d$-dimensional gaussians from a sequence of independent random samples. Our main results are upper and lower bounds giving a computationally…

Machine Learning · Computer Science 2015-05-19 Moritz Hardt , Eric Price

Deep Gaussian Processes learn probabilistic data representations for supervised learning by cascading multiple Gaussian Processes. While this model family promises flexible predictive distributions, exact inference is not tractable.…

Machine Learning · Statistics 2020-10-23 Jakob Lindinger , David Reeb , Christoph Lippert , Barbara Rakitsch

In many applications, data is collected in batches, some of which are corrupt or even adversarial. Recent work derived optimal robust algorithms for estimating discrete distributions in this setting. We consider a general framework of…

Machine Learning · Statistics 2020-02-26 Ayush Jain , Alon Orlitsky

Gradient clipping is a fundamental tool in Deep Learning, improving the high-probability convergence of stochastic first-order methods like SGD, AdaGrad, and Adam under heavy-tailed noise, which is common in training large language models.…

Machine Learning · Computer Science 2025-09-30 Saleh Vatan Khah , Savelii Chezhegov , Shahrokh Farahmand , Samuel Horváth , Eduard Gorbunov

Adaptivity is an important feature of data analysis---typically the choice of questions asked about a dataset depends on previous interactions with the same dataset. However, generalization error is typically bounded in a non-adaptive…

Machine Learning · Computer Science 2015-11-11 Raef Bassily , Adam Smith , Thomas Steinke , Jonathan Ullman

In statistical learning theory, a generalization bound usually involves a complexity measure imposed by the considered theoretical framework. This limits the scope of such bounds, as other forms of capacity measures or regularizations are…

Machine Learning · Statistics 2024-02-22 Paul Viallard , Rémi Emonet , Amaury Habrard , Emilie Morvant , Valentina Zantedeschi

Dependency networks (Heckerman et al., 2000) provide a flexible framework for modeling complex systems with many variables by combining independently learned local conditional distributions through pseudo-Gibbs sampling. Despite their…

Machine Learning · Computer Science 2026-04-02 Kazuya Takabatake , Shotaro Akaho

The posterior variance of Gaussian processes is a valuable measure of the learning error which is exploited in various applications such as safe reinforcement learning and control design. However, suitable analysis of the posterior variance…

Machine Learning · Computer Science 2019-06-05 Armin Lederer , Jonas Umlauft , Sandra Hirche

This work represents a natural coalescence of two important lines of work: learning mixtures of Gaussians and algorithmic robust statistics. In particular we give the first provably robust algorithm for learning mixtures of any constant…

Data Structures and Algorithms · Computer Science 2021-07-27 Allen Liu , Ankur Moitra

A novel, non-trivial, probabilistic upper bound on the entropy of an unknown one-dimensional distribution, given the support of the distribution and a sample from that distribution, is presented. No knowledge beyond the support of the…

Information Theory · Computer Science 2007-07-13 Joseph DeStefano , Erik Learned-Miller

The last few years have seen a surge of work on high dimensional statistics under privacy constraints, mostly following two main lines of work: the ``worst case'' line, which does not make any distributional assumptions on the input data;…

Statistics Theory · Mathematics 2022-08-17 Omri Ben-Eliezer , Dan Mikulincer , Ilias Zadik

The analytic inference, e.g. predictive distribution being in closed form, may be an appealing benefit for machine learning practitioners when they treat wide neural networks as Gaussian process in Bayesian setting. The realistic widths,…

Disordered Systems and Neural Networks · Physics 2023-08-01 Chi-Ken Lu