English
Related papers

Related papers: Deformed Statistics Kullback-Leibler Divergence Mi…

200 papers

Both the Kullback-Leibler and the Tsallis divergence have a strong limitation: if the value $0$ appears in probability distributions $\left( p_{1},\cdots ,p_{n}\right)$ and $\left( q_{1},\cdots ,q_{n}\right)$, it must appear in the same…

Statistical Mechanics · Physics 2014-10-21 Shigeru Furuichi , Flavia-Corina Mitroi-Symeonidis , Eleutherius Symeonidis

In a regression setup with deterministic design, we study the pure aggregation problem and introduce a natural extension from the Gaussian distribution to distributions in the exponential family. While this extension bears strong…

Machine Learning · Statistics 2012-06-06 Philippe Rigollet

Diffusion models are a new class of generative models that revolve around the estimation of the score function associated with a stochastic differential equation. Subsequent to its acquisition, the approximated score function is then…

Statistics Theory · Mathematics 2024-09-13 Giovanni Conforti , Alain Durmus , Marta Gentiloni Silveri

There are three classical divergence measures exist in the literature on information theory and statistics. These are namely, Jeffryes-Kullback-Leiber J-divergence. Sibson-Burbea-Rao Jensen-Shannon divegernce and Taneja Arithmetic-Geometric…

Information Theory · Computer Science 2011-04-01 Inder Jeet Taneja

The aim of this paper is to introduce new statistical criterions for estimation, suitable for inference in models with common continuous support. This proposal is in the direct line of a renewed interest for divergence based inference tools…

Statistics Theory · Mathematics 2015-03-19 Michel Broniatowski , Aida Toma , Igor Vajda

This work studies the variation in Kullback-Leibler divergence between random draws from some popular nonparametric processes and their baseline measure. In particular we focus on the Dirichlet process, the P\'olya tree and the frequentist…

Methodology · Statistics 2014-11-25 James Watson , Luis Nieto-Barajas , Chris Holmes

We answer one of the main questions in generalized descriptive set theory, the Friedman-Hyttinen-Kulikov conjecture on the Borel reducibility of the Main Gap. We show a correlation between Shelah's Main Gap and generalized Borel…

Logic · Mathematics 2024-10-02 Miguel Moreno

This paper deals with a new Bayesian approach to the standard one-sample $z$- and $t$- tests. More specifically, let $x_1,\ldots,x_n$ be an independent random sample from a normal distribution with mean $\mu$ and variance $\sigma^2$. The…

Statistics Theory · Mathematics 2020-04-01 Ibrahim Abdelrazeq , Luai Al-Labadi

In this paper we develop perturbation theory on the reduced space of a principal $G-$bundle. This theory uses a multiscale method and is related to vibrodynamics. For a fast oscillating motion with the symmetry Lie group $G$, we prove that…

Mathematical Physics · Physics 2017-04-05 Cheng Yang

A well-known technique in estimating probabilities of rare events in general and in information theory in particular (used, e.g., in the sphere-packing bound), is that of finding a reference probability measure under which the event of…

Information Theory · Computer Science 2014-12-23 Rami Atar , Neri Merhav

When we consider canonical averages for classical discrete systems, typically referred to as substitutional alloys, the map phi from many-body interatomic interactions to thermodynamic equilibrium configurations generally exhibits…

Statistical Mechanics · Physics 2026-05-12 Koretaka Yuge

A principled framework to generalize variational perturbation approximations (VPA's) formulated within the ambit of the nonadditive statistics of Tsallis statistics, is introduced. This is accomplished by operating on the terms constituting…

Statistical Mechanics · Physics 2015-05-14 R. C. Venkatesan , A. Plastino

We show that the log-likelihood of several probabilistic graphical models is Lipschitz continuous with respect to the lp-norm of the parameters. We discuss several implications of Lipschitz parametrization. We present an upper bound of the…

Machine Learning · Computer Science 2018-11-16 Jean Honorio

We propose a method to fuse posterior distributions learned from heterogeneous datasets. Our algorithm relies on a mean field assumption for both the fused model and the individual dataset posteriors and proceeds using a simple…

Machine Learning · Computer Science 2020-07-14 Sebastian Claici , Mikhail Yurochkin , Soumya Ghosh , Justin Solomon

Loss-based clustering methods, such as k-means and its variants, are standard tools for finding groups in data. However, the lack of quantification of uncertainty in the estimated clusters is a disadvantage. Model-based clustering based on…

Methodology · Statistics 2020-06-11 Tommaso Rigon , Amy H. Herring , David B. Dunson

This archiving article consists of several short reports on the discussions between the two authors over the past two years at Oxford and Madrid, and their work carried out during that period on the upper bound of the Kullback-Leibler…

Information Theory · Computer Science 2019-11-20 Min Chen , Mateu Sbert

We extend the celebrated Glivenko-Cantelli theorem, sometimes called the fundamental theorem of statistics, from its standard setting of total variation distance to all $f$-divergences. A key obstacle in this endeavor is to define…

Statistics Theory · Mathematics 2025-03-25 Haoming Wang , Lek-Heng Lim

We review recent results about the maximal values of the Kullback-Leibler information divergence from statistical models defined by neural networks, including naive Bayes models, restricted Boltzmann machines, deep belief networks, and…

Statistics Theory · Mathematics 2014-06-18 Guido Montufar , Johannes Rauh , Nihat Ay

In this paper we study the quantum generalisation of the skew divergence, which is a dissimilarity measure between distributions introduced by L. Lee in the context of natural language processing. We provide an in-depth study of the quantum…

Mathematical Physics · Physics 2015-06-15 Koenraad M. R. Audenaert

We develop a unified Data Processing Inequality PAC-Bayesian framework -- abbreviated DPI-PAC-Bayesian -- for deriving generalization error bounds in the supervised learning setting. By embedding the Data Processing Inequality (DPI) into…

Information Theory · Computer Science 2025-08-26 Muhan Guan , Farhad Farokhi , Jingge Zhu