English
Related papers

Related papers: E-Values for Exponential Families: the General Cas…

200 papers

We provide a general condition under which e-variables in the form of a simple-vs.-simple likelihood ratio exist when the null hypothesis is a composite, multivariate exponential family. Such `simple' e-variables are easy to compute and…

Methodology · Statistics 2025-04-02 Peter Grünwald , Tyron Lardy , Yunda Hao , Shaul K. Bar-Lev , Martijn de Jong

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

We consider testing a composite null hypothesis $\mathcal{P}$ against a point alternative $\mathsf{Q}$ using e-variables, which are nonnegative random variables $X$ such that $\mathbb{E}_\mathsf{P}[X] \leq 1$ for every $\mathsf{P} \in…

Statistics Theory · Mathematics 2025-02-04 Martin Larsson , Aaditya Ramdas , Johannes Ruf

Information projections have found important applications in probability theory, statistics, and related areas. In the field of hypothesis testing in particular, the reverse information projection (RIPr) has recently been shown to lead to…

Information Theory · Computer Science 2024-07-31 Tyron Lardy , Peter Grünwald , Peter Harremoës

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 consider growth-optimal e-variables with maximal e-power, both in an absolute and relative sense, for simple null hypotheses for a $d$-dimensional random vector, and multivariate composite alternatives represented as a set of…

Information Theory · Computer Science 2024-12-30 Peter Grünwald , Yunda Hao , Akshay Balsubramani

This paper investigates maximizers of the information divergence from an exponential family $E$. It is shown that the $rI$-projection of a maximizer $P$ to $E$ is a convex combination of $P$ and a probability measure $P_-$ with disjoint…

Information Theory · Computer Science 2014-06-18 Johannes Rauh

E-variables are nonnegative random variables with expected value at most one under any distribution from a given null hypothesis. Every nonasymptotically valid test can be obtained by thresholding some e-variable. As such, e-variables arise…

Statistics Theory · Mathematics 2026-02-06 Martin Larsson , Aaditya Ramdas , Johannes Ruf

E-variables enable safe and anytime-valid inference, with log-optimal e-variables given by the likelihood ratio of the least favorable distributions (LFDs) when they exist in composite settings. While this unconstrained theory is well…

Methodology · Statistics 2026-04-24 Aytijhya Saha , Aaditya Ramdas

Exponential family extensions of principal component analysis (EPCA) have received a considerable amount of attention in recent years, demonstrating the growing need for basic modeling tools that do not assume the squared loss or Gaussian…

Machine Learning · Computer Science 2012-03-19 Arto Klami , Seppo Virtanen , Samuel Kaski

We develop E-variables for testing whether two or more data streams come from the same source or not, and more generally, whether the difference between the sources is larger than some minimal effect size. These E-variables lead to exact,…

Methodology · Statistics 2022-06-23 Rosanne Turner , Alexander Ly , Peter Grünwald

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 derive the unique e-values with optimal (relative) growth rate in the worst case for testing the mean of a bounded random variable, hereby contributing with the first application beyond the assumption of mutually absolutely continuous…

Statistics Theory · Mathematics 2026-01-19 Sebastian Arnold , Eugenio Clerico

Variational autoencoders (VAE) often use Gaussian or category distribution to model the inference process. This puts a limit on variational learning because this simplified assumption does not match the true posterior distribution, which is…

Machine Learning · Computer Science 2017-02-28 Ke Sun , Xiangliang Zhang

In this paper we de ne conditional random elds in reproducing kernel Hilbert spaces and show connections to Gaussian Process classi cation. More speci cally, we prove decomposition results for undirected graphical models and we give…

Machine Learning · Computer Science 2012-07-19 Yasemin Altun , Alex Smola , Thomas Hofmann

It is shown that a consistent application of Bayesian updating from a prior probability density to a posterior using evidence in the form of expectation constraints leads to exactly the same results as the application of the maximum entropy…

Data Analysis, Statistics and Probability · Physics 2016-05-02 Sergio Davis

One of the main approaches used to construct prior distributions for objective Bayes methods is the concept of random imaginary observations. Under this setup, the expected-posterior prior (EPP) offers several advantages, among which it has…

Methodology · Statistics 2020-10-09 Dimitris Fouskakis , Ioannis Ntzoufras

In the context of the expected-posterior prior (EPP) approach to Bayesian variable selection in linear models, we combine ideas from power-prior and unit-information-prior methodologies to simultaneously produce a minimally-informative…

Computation · Statistics 2015-04-27 Dimitris Fouskakis , Ioannis Ntzoufras , David Draper

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

The power-expected-posterior (PEP) prior is an objective prior for Gaussian linear models, which leads to consistent model selection inference, under the M-closed scenario, and tends to favor parsimonious models. Recently, two new forms of…

Methodology · Statistics 2019-11-22 Dimitris Fouskakis , Ioannis Ntzoufras , Konstantinos Perrakis
‹ Prev 1 2 3 10 Next ›