English
Related papers

Related papers: Optimally approximating exponential families

200 papers

We propose a novel approach for density estimation with exponential families for the case when the true density may not fall within the chosen family. Our approach augments the sufficient statistics with features designed to accumulate…

Machine Learning · Statistics 2012-09-07 Lin Yuan , Sergey Kirshner , Robert Givan

We consider on-line density estimation with a parameterized density from the exponential family. The on-line algorithm receives one example at a time and maintains a parameter that is essentially an average of the past examples. After…

Machine Learning · Computer Science 2013-01-30 Katy S. Azoury , Manfred K. Warmuth

In this paper we revisit the classical method of partitioning classification and study its convergence rate under relaxed conditions, both for observable (non-privatised) and for privatised data. We consider the problem of classification in…

Machine Learning · Statistics 2025-09-09 Balázs Csanád Csáji , László Györfi , Ambrus Tamás , Harro Walk

We consider the classical problem of learning, with arbitrary accuracy, the natural parameters of a $k$-parameter truncated \textit{minimal} exponential family from i.i.d. samples in a computationally and statistically efficient manner. We…

Machine Learning · Computer Science 2023-09-13 Abhin Shah , Devavrat Shah , Gregory W. Wornell

We introduce Exponential Family Discriminant Analysis (EFDA), a unified generative framework that extends classical Linear Discriminant Analysis (LDA) beyond the Gaussian setting to any member of the exponential family. Under the assumption…

Machine Learning · Computer Science 2026-03-25 Anish Lakkapragada

In a regular full exponential family, the maximum likelihood estimator (MLE) need not exist in the traditional sense. However, the MLE may exist in the completion of the exponential family. Existing algorithms for finding the MLE in the…

Statistics Theory · Mathematics 2020-11-30 Daniel J. Eck , Charles J. Geyer

We develop and compare e-variables for testing whether $k$ samples of data are drawn from the same distribution, the alternative being that they come from different elements of an exponential family. We consider the GRO (growth-rate…

Methodology · Statistics 2024-01-09 Yunda Hao , Peter Grünwald , Tyron Lardy , Long Long , Reuben Adams

Exponential families are the workhorses of parametric modelling theory. One reason for their popularity is their associated inference theory, which is very clean, both from a theoretical and a computational point of view. One way in which…

Statistics Theory · Mathematics 2007-09-14 Karim Anaya-Izquierdo , Paul Marriott

Chernoff information upper bounds the probability of error of the optimal Bayesian decision rule for $2$-class classification problems. However, it turns out that in practice the Chernoff bound is hard to calculate or even approximate. In…

Information Theory · Computer Science 2021-04-29 Frank Nielsen

Exponential families encompass the distributions central to modern machine learning -- softmax, Gaussians, and Boltzmann distributions -- and underlie the theory of variational inference, entropy-regularized reinforcement learning, and…

Machine Learning · Computer Science 2026-05-01 Marc Dymetman

This thesis studies high-dimensional, continuous-valued pairwise Markov Random Fields. We are particularly interested in approximating pairwise densities whose logarithm belongs to a Sobolev space. For this problem we propose the method of…

Statistics Theory · Mathematics 2015-06-12 Eric Janofsky

The EM (Expectation-Maximization) algorithm is regarded as an MM (Majorization-Minimization) algorithm for maximum likelihood estimation of statistical models. Expanding this view, this paper demonstrates that by choosing an appropriate…

Optimization and Control · Mathematics 2026-02-12 Kensuke Asai , Jun-ya Gotoh

Learning of continuous exponential family distributions with unbounded support remains an important area of research for both theory and applications in high-dimensional statistics. In recent years, score matching has become a widely used…

Machine Learning · Computer Science 2026-05-15 Devin Smedira , Abhijith Jayakumar , Sidhant Misra , Marc Vuffray , Andrey Y. Lokhov

This article considers exponential families of truncated multivariate normal distributions with one-sided truncation for some or all coordinates. We observe that if all components are one-sided truncated then this family is not full. The…

Statistics Theory · Mathematics 2025-07-02 Michael Levine , Donald Richards , Jianxi Su

In this paper, we consider an infinite dimensional exponential family, $\mathcal{P}$ of probability densities, which are parametrized by functions in a reproducing kernel Hilbert space, $H$ and show it to be quite rich in the sense that a…

Statistics Theory · Mathematics 2017-05-29 Bharath Sriperumbudur , Kenji Fukumizu , Arthur Gretton , Aapo Hyvärinen , Revant Kumar

The minimum message length principle is an information theoretic criterion that links data compression with statistical inference. This paper studies the strict minimum message length (SMML) estimator for $d$-dimensional exponential…

Information Theory · Computer Science 2014-03-24 James G. Dowty

We consider the problem of computing the maximum likelihood multivariate log-concave distribution for a set of points. Specifically, we present an algorithm which, given $n$ points in $\mathbb{R}^d$ and an accuracy parameter $\epsilon>0$,…

Data Structures and Algorithms · Computer Science 2019-07-22 Brian Axelrod , Ilias Diakonikolas , Anastasios Sidiropoulos , Alistair Stewart , Gregory Valiant

The article is devoted to the study of exponential statistical structures of type B, which constitute a subclass of exponential families of probability distributions. This class is characterized by a number of analytical and probabilistic…

Statistics Theory · Mathematics 2025-12-23 Oleksandr Volkov , Yurii Volkov

The closure of a discrete exponential family is described by a finite set of equations corresponding to the circuits of an underlying oriented matroid. These equations are similar to the equations used in algebraic statistics, although they…

Statistics Theory · Mathematics 2011-09-19 Johannes Rauh , Thomas Kahle , Nihat Ay

We investigate penalized maximum log-likelihood estimation for exponential family distributions whose natural parameter resides in a reproducing kernel Hilbert space. Key to our approach is a novel technique, doubly dual embedding, that…

Machine Learning · Computer Science 2019-04-25 Bo Dai , Hanjun Dai , Arthur Gretton , Le Song , Dale Schuurmans , Niao He