English
Related papers

Related papers: Bregman Deviations of Generic Exponential Families

200 papers

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

Density-based minimum divergence procedures represent popular techniques in parametric statistical inference. They combine strong robustness properties with high (sometimes full) asymptotic efficiency. Among density-based minimum distance…

Methodology · Statistics 2020-12-23 Pushpinder Singh , Abhijit Mandal , Ayanendranath Basu

We obtain optimal moment bounds for Birkhoff sums, and optimal concentration inequalities, for a large class of slowly mixing dynamical systems, including those that admit anomalous diffusion in the form of a stable law or a central limit…

Dynamical Systems · Mathematics 2017-09-01 Sébastien Gouëzel , Ian Melbourne

The success of large generative models has driven a paradigm shift, leveraging massive multi-source data to enhance model capabilities. However, the interaction among these sources remains theoretically underexplored. This paper takes the…

Machine Learning · Computer Science 2025-07-09 Rongzhen Wang , Yan Zhang , Chenyu Zheng , Chongxuan Li , Guoqiang Wu

We establish concentration rates for estimation of treatment effects in experiments that incorporate prior sources of information -- such as past pilots, related studies, or expert assessments -- whose external validity is uncertain. Each…

Econometrics · Economics 2026-03-24 Frederico Finan , Demian Pouzo

Exponential-family harmoniums (EFHs), which extend restricted Boltzmann machines (RBMs) from Bernoulli random variables to other exponential families (Welling et al., 2005), are generative models that can be trained with…

Machine Learning · Computer Science 2016-05-20 Joseph G. Makin , Benjamin K. Dichter , Philip N. Sabes

A classic problem in statistics is the estimation of the expectation of random variables from samples. This gives rise to the tightly connected problems of deriving concentration inequalities and confidence sequences, that is confidence…

Machine Learning · Statistics 2022-08-02 Francesco Orabona , Kwang-Sung Jun

Empirical evidence shows that ensembles, such as bagging, boosting, random and rotation forests, generally perform better in terms of their generalization error than individual classifiers. To explain this performance, Schapire et al.…

Machine Learning · Statistics 2019-06-10 Waldyn Martinez , J. Brian Gray

We present a general method for deriving collapsed variational inference algo- rithms for probabilistic models in the conjugate exponential family. Our method unifies many existing approaches to collapsed variational inference. Our…

Machine Learning · Computer Science 2012-12-05 James Hensman , Magnus Rattray , Neil D. Lawrence

We obtain a Bernstein type Gaussian concentration inequality for martingales. Our inequality improves the Azuma-Hoeffding inequality for moderate deviations $x$. Following the work of McDiarmid (1989), Talagrand (1996) and Boucheron, Lugosi…

Probability · Mathematics 2017-10-17 Xiequan Fan

This work introduces the minimax Laplace transform method, a modification of the cumulant-based matrix Laplace transform method developed in "User-friendly tail bounds for sums of random matrices" (arXiv:1004.4389v6) that yields both upper…

Probability · Mathematics 2011-07-22 Alex Gittens , Joel A. Tropp

Dirichlet process mixtures are flexible non-parametric models, particularly suited to density estimation and probabilistic clustering. In this work we study the posterior distribution induced by Dirichlet process mixtures as the sample size…

Statistics Theory · Mathematics 2022-11-29 Filippo Ascolani , Antonio Lijoi , Giovanni Rebaudo , Giacomo Zanella

Freedman's inequality is a martingale counterpart to Bernstein's inequality. This result shows that the large-deviation behavior of a martingale is controlled by the predictable quadratic variation and a uniform upper bound for the…

Probability · Mathematics 2015-03-17 Joel A. Tropp

We are concerned with obtaining novel concentration inequalities for the missing mass, i.e. the total probability mass of the outcomes not observed in the sample. We not only derive - for the first time - distribution-free Bernstein-like…

Machine Learning · Statistics 2015-06-22 Bahman Yari Saeed Khanloo , Gholamreza Haffari

We consider Gibbs measures on the configuration space $S^{\mathbb{Z}^d}$, where mostly $d\geq 2$ and $S$ is a finite set. We start by a short review on concentration inequalities for Gibbs measures. In the Dobrushin uniqueness regime, we…

Probability · Mathematics 2017-10-25 J. -R. Chazottes , P. Collet , F. Redig

For the uniform random regular directed graph we prove concentration inequalities for (1) codegrees and (2) the number of edges passing from one set of vertices to another. As a consequence, we can deduce discrepancy properties for the…

Combinatorics · Mathematics 2015-10-27 Nicholas A. Cook

In this paper, we study the risk bounds for samples independently drawn from an infinitely divisible (ID) distribution. In particular, based on a martingale method, we develop two deviation inequalities for a sequence of random variables of…

Machine Learning · Statistics 2012-02-20 Chao Zhang , Dacheng Tao

The method to derive uniform bounds with Gaussian and Rademacher complexities is extended to the case where the sample average is replaced by a nonlinear statistic. Tight bounds are obtained for U-statistics, smoothened L-statistics and…

Statistics Theory · Mathematics 2019-05-13 Andreas Maurer , Massimiliano Pontil

We establish bounds on the conductance for the systematic-scan and random-scan Gibbs samplers when the target distribution satisfies a Poincar\'e or log-Sobolev inequality and possesses sufficiently regular conditional distributions. These…

Statistics Theory · Mathematics 2026-04-28 Alexander Goyal , George Deligiannidis , Nikolas Kantas

A novel method for estimating Bayesian network (BN) parameters from data is presented which provides improved performance on test data. Previous research has shown the value of representing conditional probability distributions (CPDs) via…

Machine Learning · Computer Science 2013-01-14 Geoff A. Jarrad