English
Related papers

Related papers: Relationship between the Bregman divergence and be…

200 papers

In this paper, an optimal inequality involving the delta curvature is exposed. An application of Riemannian submersions dealing meteorology is presented. Some characterizations about the vertical motion and the horizontal divergence are…

Differential Geometry · Mathematics 2019-10-01 Mehmet Gulbahar , Semsi Eken Meric , Erol Kilic

The measurement of the efficiency of an event selection is always an important part of the analysis of experimental data. The statistical techniques which are needed to determine the efficiency and its uncertainty are reviewed. Frequentist…

Data Analysis, Statistics and Probability · Physics 2012-08-28 Diego Casadei

We give some conditions under which (uniform) convergence of a family of Dirichlet series to another Dirichlet series implies the convergence of their individual coefficients and/or exponents. We give some applications to some spectral zeta…

Classical Analysis and ODEs · Mathematics 2015-09-15 Gunther Cornelissen , Aristides Kontogeorgis

We study two variants of the mirror descent-ascent (MDA) algorithm for solving min-max problems on the space of measures: simultaneous and alternating. We work under assumptions of convexity-concavity and relative smoothness of the payoff…

Optimization and Control · Mathematics 2026-05-08 Razvan-Andrei Lascu , Mateusz B. Majka , Łukasz Szpruch

An important problem in machine learning theory is to understand the approximation and generalization properties of two-layer neural networks in high dimensions. To this end, researchers have introduced the Barron space…

Machine Learning · Statistics 2024-01-02 Lei Wu

As well known, the study of Riemanns zeta function {\zeta}(s) involves the related entire function {\xi}(s). A close relative of {\zeta}(s) is the alternating zeta function {\eta}(s). Similar to {\zeta}(s), also {\eta}(s) has a…

Number Theory · Mathematics 2016-10-24 Renaat Van Malderen

Beta regression has been extensively used by statisticians and practitioners to model bounded continuous data and there is no strong and similar competitor having its main features. A class of normalized inverse-Gaussian (N-IG) process was…

Methodology · Statistics 2020-03-12 Wagner Barreto-Souza , Vinícius D. Mayrink , Alexandre B. Simas

This paper discusses the incomplete Gamma and Beta integrals involving the generalised hypergeometric function. The distribution of the largest and the smallest roots of a ratio arising in comparing the mean differences among groups is…

Statistics Theory · Mathematics 2026-04-24 Haoming Wang

The $\beta$-shift is the transformation from the unit interval to itself that maps $x$ to the fractional part of $\beta x$. Permutations realized by the relative order of the elements in the orbits of these maps have been studied for…

Combinatorics · Mathematics 2016-11-18 Sergi Elizalde , Katherine Moore

In knowledge graph embedding, the theoretical relationship between the softmax cross-entropy and negative sampling loss functions has not been investigated. This makes it difficult to fairly compare the results of the two different loss…

Machine Learning · Computer Science 2022-03-17 Hidetaka Kamigaito , Katsuhiko Hayashi

Optimization problems, generalized equations, and the multitude of other variational problems invariably lead to the analysis of sets and set-valued mappings as well as their approximations. We review the central concept of set-convergence…

Optimization and Control · Mathematics 2020-02-25 Johannes O. Royset

This paper discusses basic results and recent developments on variational regularization methods, as developed for inverse problems. In a typical setup we review basic properties needed to obtain a convergent regularization scheme and…

Machine Learning · Computer Science 2021-12-10 Martin Burger

We introduce a class of strongly \'{e}tale difference algebras, whose role in the study of difference equations is analogous to the role of \'{e}tale algebras in the study of algebraic equations. We deduce an improved version of Babbitt's…

Algebraic Geometry · Mathematics 2018-02-23 Ivan Tomašić , Michael Wibmer

This paper is focused on $f$-divergences, consisting of three main contributions. The first one introduces integral representations of a general $f$-divergence by means of the relative information spectrum. The second part provides a new…

Information Theory · Computer Science 2018-07-04 Igal Sason

Regression models are used for inference and prediction in a wide range of applications providing a powerful scientific tool for researchers and analysts from different fields. In many research fields the amount of available data as well as…

Methodology · Statistics 2018-06-08 Aliaksandr Hubin , Geir Storvik , Florian Frommlet

This work obtains sharp closed-form exponential concentration inequalities of Bernstein type for the ubiquitous beta distribution, improving upon sub-gaussian and sub-gamma bounds previously studied in this context. The proof leverages a…

Probability · Mathematics 2024-10-21 Maciej Skorski

We explore a more general class of soft supersymmetry-breaking masses and interactions than that usually considered, both in general and in the MSSM context, where our results for the one-loop $\beta$-functions correct some errors in the…

High Energy Physics - Phenomenology · Physics 2009-10-31 I. Jack , D. R. T. Jones

We obtain the optimal proxy variance for the sub-Gaussianity of Beta distribution, thus proving upper bounds recently conjectured by Elder (2016). We provide different proof techniques for the symmetrical (around its mean) case and the…

Statistics Theory · Mathematics 2017-10-18 Olivier Marchal , Julyan Arbel

We show that forms of Bayesian and MDL inference that are often applied to classification problems can be *inconsistent*. This means there exists a learning problem such that for all amounts of data the generalization errors of the MDL…

Statistics Theory · Mathematics 2007-07-16 Peter Grunwald , John Langford

Motivated by a probabilistic analysis of a simple game (itself inspired by a problem in computational learning theory) we introduce the \emph{moment zeta function} of a probability distribution, and study in depth some asymptotic properties…

Number Theory · Mathematics 2007-05-23 Igor Rivin