English
Related papers

Related papers: A variational approach to dimension-free self-norm…

200 papers

We derive a new closed-form variance-adaptive confidence sequence (CS) for estimating the average conditional mean of a sequence of bounded random variables. Empirically, it yields the tightest closed-form CS we have found for tracking…

Statistics Theory · Mathematics 2025-12-25 Ben Chugg , Aaditya Ramdas

We extend PAC-Bayesian theory to generative models and develop generalization bounds for models based on the Wasserstein distance and the total variation distance. Our first result on the Wasserstein distance assumes the instance space is…

Machine Learning · Computer Science 2023-11-15 Sokhna Diarra Mbacke , Florence Clerc , Pascal Germain

We establish nonuniform Berry-Esseen bounds for martingales under the conditional Bernstein condition. These bounds imply Cram\'er type large deviations for moderate $x$'s, and are of exponential decay rate as de la Pe\~na's inequality when…

Probability · Mathematics 2017-08-03 Xiequan Fan , Ion Grama , Quansheng Liu

Self-normalized processes are basic to many probabilistic and statistical studies. They arise naturally in the the study of stochastic integrals, martingale inequalities and limit theorems, likelihood-based methods in hypothesis testing and…

Probability · Mathematics 2009-09-29 Victor H. de la Peña , Michael J. Klass , Tze Leung Lai

Concentration inequalities quantify the deviation of a random variable from a fixed value. In spite of numerous applications, such as opinion surveys or ecological counting procedures, few concentration results are known for the setting of…

Statistics Theory · Mathematics 2015-07-28 Rémi Bardenet , Odalric-Ambrym Maillard

In this paper we provide general conditions to check on the model and the prior to derive posterior concentration rates for data-dependent priors (or empirical Bayes approaches). We aim at providing conditions that are close to the…

Statistics Theory · Mathematics 2014-06-18 Sophie Donnet , Vincent Rivoirard , Judith Rousseau , Catia Scricciolo

The Probably Approximately Correct (PAC) Bayes framework (McAllester, 1999) can incorporate knowledge about the learning algorithm and (data) distribution through the use of distribution-dependent priors, yielding tighter generalization…

Machine Learning · Computer Science 2019-04-22 Gintare Karolina Dziugaite , Daniel M. Roy

We give a novel, unified derivation of conditional PAC-Bayesian and mutual information (MI) generalization bounds. We derive conditional MI bounds as an instance, with special choice of prior, of conditional MAC-Bayesian (Mean Approximately…

Machine Learning · Computer Science 2021-06-18 Peter Grünwald , Thomas Steinke , Lydia Zakynthinou

Constant-stepsize stochastic approximation (SA) is widely used in learning for computational efficiency. For a fixed stepsize, the iterates typically admit a stationary distribution that is rarely tractable. Prior work shows that as the…

Machine Learning · Computer Science 2026-02-17 Zedong Wang , Yuyang Wang , Ijay Narang , Felix Wang , Yuzhou Wang , Siva Theja Maguluri

We give a distribution-dependent concentration inequality for functions of independent variables. The result extends Bernstein's inequality from sums to more general functions, whose variation in any argument does not depend too much on the…

Probability · Mathematics 2017-05-12 Andreas Maurer

Variational inference (VI) is widely used for approximate inference in Bayesian machine learning. In addition to this practical success, generalization bounds for variational inference and related algorithms have been developed, mostly…

Machine Learning · Computer Science 2025-02-19 Yadi Wei , Roni Khardon

We present a general approach, based on exponential inequalities, to derive bounds on the generalization error of randomized learning algorithms. Using this approach, we provide bounds on the average generalization error as well as bounds…

Machine Learning · Computer Science 2023-03-10 Fredrik Hellström , Giuseppe Durisi

Variational Bayesian Inference is a popular methodology for approximating posterior distributions over Bayesian neural network weights. Recent work developing this class of methods has explored ever richer parameterizations of the…

We present a discretization-free scalable framework for solving a large class of mass-conserving partial differential equations (PDEs), including the time-dependent Fokker-Planck equation and the Wasserstein gradient flow. The main…

Machine Learning · Computer Science 2023-11-15 Lingxiao Li , Samuel Hurault , Justin Solomon

This paper studies quasi Bayesian estimation and uncertainty quantification for an unknown function that is identified by a nonparametric conditional moment restriction. We derive contraction rates for a class of Gaussian process priors.…

Econometrics · Economics 2023-11-08 Sid Kankanala

This note describes non-asymptotic variance and tail bounds for order statistics of samples of independent identically distributed random variables. Those bounds are checked to be asymptotically tight when the sampling distribution belongs…

Probability · Mathematics 2012-11-05 Stephane Boucheron , Maud Thomas

The aim of this paper is to study, in the infinite dimensional framework, the existence and uniqueness for the solution of the following multivalued generalized backward stochastic differential equation, considered on a random, possibly…

Probability · Mathematics 2015-10-30 Lucian Maticiuc , Aurel Răşcanu

The aim of this paper is to show that a probability measure concentrates independently of the dimension like a gaussian measure if and only if it verifies Talagrand's $\T_2$ transportation-cost inequality. This theorem permits us to give a…

Probability · Mathematics 2013-03-04 Nathael Gozlan

We consider the optimization of a smooth and strongly convex objective using constant step-size stochastic gradient descent (SGD) and study its properties through the prism of Markov chains. We show that, for unbiased gradient estimates…

Machine Learning · Statistics 2025-11-25 Ibrahim Merad , Stéphane Gaïffas

We provide a novel dimension-free uniform concentration bound for the empirical risk function of constrained logistic regression. Our bound yields a milder sufficient condition for a uniform law of large numbers than conditions derived by…

Statistics Theory · Mathematics 2024-10-15 Shogo Nakakita