English
Related papers

Related papers: Novel Bernstein-like Concentration Inequalities fo…

200 papers

We prove an extension of McDiarmid's inequality for metric spaces with unbounded diameter. To this end, we introduce the notion of the {\em subgaussian diameter}, which is a distribution-dependent refinement of the metric diameter. Our…

Probability · Mathematics 2013-09-12 Aryeh Kontorovich

In the paper, the authors review origins, motivations, and generalizations of a series of inequalities involving several exponential functions and sums, establish three new inequalities involving finite exponential functions and sums by…

Classical Analysis and ODEs · Mathematics 2020-08-26 Feng Qi , Bai-Ni Guo

Self-normalized processes arise naturally in many learning-related tasks. While self-normalized concentration has been extensively studied for scalar-valued processes, there are few results for multidimensional processes outside of the…

Probability · Mathematics 2025-05-02 Justin Whitehouse , Zhiwei Steven Wu , Aaditya Ramdas

This paper is devoted to establishing exponential bounds for the probabilities of deviation of a sample sum from its expectation, when the variables involved in the summation are obtained by sampling in a finite population according to a…

Statistics Theory · Mathematics 2016-10-13 Patrice Bertail , Stephan Clémençon

Novelty detection is commonly referred to as the discrimination of observations that do not conform to a learned model of regularity. Despite its importance in different application settings, designing a novelty detector is utterly complex…

Computer Vision and Pattern Recognition · Computer Science 2019-03-07 Davide Abati , Angelo Porrello , Simone Calderara , Rita Cucchiara

We establish a new Bernstein-type deviation inequality for general (non-reversible) discrete-time Markov chains via an elementary approach. More robust than existing works in the literature, our result only requires the Markov chain to…

Probability · Mathematics 2025-10-07 De Huang , Xiangyuan Li

We study problem-dependent rates, i.e., generalization errors that scale near-optimally with the variance, the effective loss, or the gradient norms evaluated at the "best hypothesis." We introduce a principled framework dubbed "uniform…

Machine Learning · Statistics 2020-12-25 Yunbei Xu , Assaf Zeevi

We present a novel approach to estimating discrete distributions with (potentially) infinite support in the total variation metric. In a departure from the established paradigm, we make no structural assumptions whatsoever on the sampling…

Statistics Theory · Mathematics 2020-10-16 Doron Cohen , Aryeh Kontorovich , Geoffrey Wolfer

We address the problem of learning an unknown smooth function and its derivatives from noisy pointwise evaluations under the supremum norm. While classical nonparametric regression provides a strong theoretical foundation, traditional…

Machine Learning · Computer Science 2026-03-10 Davide Maran , Marcello Restelli

We study full Bayesian procedures for sparse linear regression when errors have a symmetric but otherwise unknown distribution. The unknown error distribution is endowed with a symmetrized Dirichlet process mixture of Gaussians. For the…

Statistics Theory · Mathematics 2019-03-26 Minwoo Chae , Lizhen Lin , David B. Dunson

We consider the problem of testing a null hypothesis defined by equality and inequality constraints on a statistical parameter. Testing such hypotheses can be challenging because the number of relevant constraints may be on the same order…

Methodology · Statistics 2024-02-19 Nils Sturma , Mathias Drton , Dennis Leung

The lossless data compression algorithm based on Bayesian Attention Networks is derived from first principles. Bayesian Attention Networks are defined by introducing an attention factor per a training sample loss as a function of two sample…

Machine Learning · Computer Science 2021-03-30 Michael Tetelman

We establish a Berry--Esseen bound for general multivariate nonlinear statistics by developing a new multivariate-type randomized concentration inequality. The bound is the best possible for many known statistics. As applications,…

Probability · Mathematics 2021-04-02 Qi-Man Shao , Zhuo-Song Zhang

Change of measure inequalities translate divergences between probability measures into explicit bounds on event probabilities, and play an important role in deriving probabilistic guarantees in learning theory, information theory, and…

Information Theory · Computer Science 2026-05-28 Yanxiao Liu , Yijun Fan , Deniz Gündüz

We derive tight and computable bounds on the bias of statistical estimators, or more generally of quantities of interest, when evaluated on a baseline model P rather than on the typically unknown true model Q. Our proposed method combines…

Information Theory · Computer Science 2017-07-04 Konstantinos Gourgoulias , Markos A. Katsoulakis , Luc Rey-Bellet , Jie Wang

Uniform and nonuniform Berry--Esseen (BE) bounds of optimal orders on the closeness to normality for general abstract nonlinear statistics are given, which are then used to obtain optimal bounds on the rate of convergence in the delta…

Statistics Theory · Mathematics 2017-01-17 Iosif Pinelis , Raymond Molzon

We revisit the method of mixture technique, also known as the Laplace method, to study the concentration phenomenon in generic exponential families. Combining the properties of Bregman divergence associated with log-partition function of…

Machine Learning · Computer Science 2023-07-14 Sayak Ray Chowdhury , Patrick Saux , Odalric-Ambrym Maillard , Aditya Gopalan

We use the generic chaining device proposed by Talagrand to establish exponential bounds on the deviation probability of some suprema of random processes. Then, given a random vector $\xi$ in $\R^{n}$ the components of which are independent…

Statistics Theory · Mathematics 2009-04-22 Yannick Baraud

Current unsupervised anomaly localization approaches rely on generative models to learn the distribution of normal images, which is later used to identify potential anomalous regions derived from errors on the reconstructed images. However,…

Image and Video Processing · Electrical Eng. & Systems 2021-10-29 Julio Silva-Rodríguez , Valery Naranjo , Jose Dolz

Langevin algorithms are gradient descent methods augmented with additive noise, and are widely used in Markov Chain Monte Carlo (MCMC) sampling, optimization, and machine learning. In recent years, the non-asymptotic analysis of Langevin…

Machine Learning · Computer Science 2023-01-10 Yuping Zheng , Andrew Lamperski