English
Related papers

Related papers: Exponential families from a single KL identity

200 papers

We consider the question of learning the natural parameters of a $k$ parameter minimal exponential family from i.i.d. samples in a computationally and statistically efficient manner. We focus on the setting where the support as well as the…

Machine Learning · Computer Science 2021-11-01 Abhin Shah , Devavrat Shah , Gregory W. Wornell

We consider parametric exponential families of dimension $K$ on the real line. We study a variant of \textit{boundary crossing probabilities} coming from the multi-armed bandit literature, in the case when the real-valued distributions form…

Machine Learning · Statistics 2017-05-25 Odalric-Ambrym Maillard

Maximum likelihood learning with exponential families leads to moment-matching of the sufficient statistics, a classic result. This can be generalized to conditional exponential families and/or when there are hidden data. This document…

Machine Learning · Computer Science 2020-01-28 Justin Domke

This article studies exponential families $\mathcal{E}$ on finite sets such that the information divergence $D(P\|\mathcal{E})$ of an arbitrary probability distribution from $\mathcal{E}$ is bounded by some constant $D>0$. A particular…

Statistics Theory · Mathematics 2014-06-18 Johannes Rauh

We propose using a discounted version of a convex combination of the log-likelihood with the corresponding expected log-likelihood such that when they are maximized they yield a filter, predictor and smoother for time series. This paper…

Methodology · Statistics 2026-04-29 Simon Donker van Heel , Neil Shephard

Expectation maximization (EM) is the default algorithm for fitting probabilistic models with missing or latent variables, yet we lack a full understanding of its non-asymptotic convergence properties. Previous works show results along the…

Machine Learning · Computer Science 2022-03-01 Frederik Kunstner , Raunak Kumar , Mark Schmidt

Exponential families are a particular class of statistical manifolds which are particularly important in statistical inference, and which appear very frequently in statistics. For example, the set of normal distributions, with mean {\mu}…

Differential Geometry · Mathematics 2015-06-04 Mathieu Molitor

Recent advances in deep learning have brought to the fore models that can make multiple computational steps in the service of completing a task; these are capable of describ- ing long-term dependencies in sequential data. Novel recurrent…

Machine Learning · Computer Science 2018-09-06 Kyriakos Tolias , Sotirios Chatzis

In this paper, we introduce a new two-parameter lifetime distribution, called the exponential-generalized truncated logarithmic (EGTL) distribution, by compounding the exponential and generalized truncated logarithmic distributions. Our…

Statistics Theory · Mathematics 2018-09-28 Mohieddine Rahmouni , Ayman Orabi

The log-linear model has received a significant amount of theoretical attention in previous decades and remains the fundamental tool used for learning probability distributions over discrete variables. Despite its large popularity in…

Machine Learning · Computer Science 2026-04-14 James Enouen , Mahito Sugiyama

In \cite{KumarS15J2}, it was shown that a generalized maximum likelihood estimation problem on a (canonical) $\alpha$-power-law model ($\mathbb{M}^{(\alpha)}$-family) can be solved by solving a system of linear equations. This was due to an…

Statistics Theory · Mathematics 2018-01-30 Atin Gayen , M. Ashok Kumar

Probabilistic graphical models that encode an underlying Markov random field are fundamental building blocks of generative modeling to learn latent representations in modern multivariate data sets with complex dependency structures. Among…

Methodology · Statistics 2025-04-03 Yujie Chen , Anindya Bhadra , Antik Chakraborty

Exponential families comprise a broad class of statistical models and parametric families like normal distributions, binomial distributions, gamma distributions or exponential distributions. Thereby the formal representation of its…

Statistics Theory · Mathematics 2020-06-23 Patrick Michl

Bayesian Likelihood-Free Inference (LFI) approaches allow to obtain posterior distributions for stochastic models with intractable likelihood, by relying on model simulations. In Approximate Bayesian Computation (ABC), a popular LFI method,…

Methodology · Statistics 2022-02-08 Lorenzo Pacchiardi , Ritabrata Dutta

Tsallis and R\'{e}nyi entropies, which are monotone transformations of each other, are deformations of the celebrated Shannon entropy. Maximization of these deformed entropies, under suitable constraints, leads to the $q$-exponential family…

Probability · Mathematics 2022-01-14 Ting-Kam Leonard Wong , Jun Zhang

The $\lambda$-exponential family generalizes the standard exponential family via a generalized convex duality motivated by optimal transport. It is the constant-curvature analogue of the exponential family from the information-geometric…

Statistics Theory · Mathematics 2025-05-07 Xiwei Tian , Ting-Kam Leonard Wong , Jiaowen Yang , Jun Zhang

We generalize the usual exponential Boltzmann factor to any reasonable and potentially observable distribution function, $B(E)$. By defining generalized logarithms $\Lambda$ as inverses of these distribution functions, we are led to a…

Statistical Mechanics · Physics 2007-05-23 Rudolf Hanel , Stefan Thurner

Exponential families are statistical models which are the workhorses in statistics, information theory, and machine learning among others. An exponential family can either be normalized subtractively by its cumulant or free energy function…

Information Theory · Computer Science 2024-02-27 Frank Nielsen

The classification of natural exponential families started with the paper \cite {Morri} where Carl Morris unifies six very familiar families by the fact that their variance functions are polynomials of degree less or equal to two. Extension…

Statistics Theory · Mathematics 2025-12-23 Abdelhanid Hassairi , Gérard Letac

Kullback-Leibler (KL) divergence is a fundamental concept in information theory that quantifies the discrepancy between two probability distributions. In the context of Variational Autoencoders (VAEs), it serves as a central regularization…

Machine Learning · Computer Science 2026-04-14 Andrés Muñoz , Rodrigo Ramele