中文
相关论文

相关论文: Limit distribution theory for $f$-Divergences

200 篇论文

Inferring and comparing complex, multivariable probability density functions is fundamental to problems in several fields, including probabilistic learning, network theory, and data analysis. Classification and prediction are the two faces…

信息论 · 计算机科学 2017-03-30 David J. Galas , T. Gregory Dewey , James Kunert-Graf , Nikita A. Sakhanenko

A parametric theory of statistical inference is developed for the moderate deviation probability zone. The new approach to the proofs is based on the Taylor series expansion of the logarithm of the likelihood ratio based on the Hellinger…

统计理论 · 数学 2026-04-28 Mikhail Ermakov

Statistical distances (SDs), which quantify the dissimilarity between probability distributions, are central to machine learning and statistics. A modern method for estimating such distances from data relies on parametrizing a variational…

统计理论 · 数学 2021-03-18 Sreejith Sreekumar , Zhengxin Zhang , Ziv Goldfeld

We prove that the $f$-divergences between univariate Cauchy distributions are all symmetric, and can be expressed as strictly increasing scalar functions of the symmetric chi-squared divergence. We report the corresponding scalar functions…

信息论 · 计算机科学 2022-12-26 Frank Nielsen , Kazuki Okamura

The Kullback-Leibler divergence, the Kullback-Leibler variation, and the Bernstein "norm" are used to quantify discrepancies among probability distributions in likelihood models such as nonparametric maximum likelihood and nonparametric…

统计理论 · 数学 2026-01-27 Tetsuya Kaji

We define a new measure of causation from a fluctuation-response theorem for Kullback-Leibler divergences, based on the information-theoretic cost of perturbations. This information response has both the invariance properties required for…

信息论 · 计算机科学 2021-10-27 Andrea Auconi , Benjamin M. Friedrich , Andrea Giansanti

This paper deals with maximization of classical $f$-divergence between the distributions of a measurement outputs of a given pair of quantum states. $f$-divergence $D_{f}$ between the probability density functions $p_{1}$ and $p_{2}$ over a…

量子物理 · 物理学 2016-06-07 Keiji Matsumoto

Information divergence functions play a critical role in statistics and information theory. In this paper we show that a non-parametric f-divergence measure can be used to provide improved bounds on the minimum binary classification…

信息论 · 计算机科学 2015-02-11 Visar Berisha , Alan Wisler , Alfred O. Hero , Andreas Spanias

Selecting an appropriate divergence measure is a critical aspect of machine learning, as it directly impacts model performance. Among the most widely used, we find the Kullback-Leibler (KL) divergence, originally introduced in kinetic…

数学物理 · 物理学 2025-07-16 Gennaro Auricchio , Giovanni Brigati , Paolo Giudici , Giuseppe Toscani

In statistical classification/multiple hypothesis testing and machine learning, a model distribution estimated from the training data is usually applied to replace the unknown true distribution in the Bayes decision rule, which introduces a…

信息论 · 计算机科学 2024-09-24 Zijian Yang , Vahe Eminyan , Ralf Schlüter , Hermann Ney

This paper is a strongly geometrical approach to the Fisher distance, which is a measure of dissimilarity between two probability distribution functions. The Fisher distance, as well as other divergence measures, are also used in many…

统计方法学 · 统计学 2014-01-13 Sueli I. R. Costa , Sandra A. Santos , João E. Strapasson

This paper develops systematic approaches to obtain $f$-divergence inequalities, dealing with pairs of probability measures defined on arbitrary alphabets. Functional domination is one such approach, where special emphasis is placed on…

信息论 · 计算机科学 2016-12-06 Igal Sason , Sergio Verdú

Optimum designs for parameter estimation in generalized regression models are standardly based on the Fisher information matrix (cf. Atkinson et al (2014) for a recent exposition). The corresponding optimality criteria are related to the…

统计理论 · 数学 2015-07-28 Katarína Burclová , Andrej Pázman

For a regression model, we consider the risk of the maximum likelihood estimator with respect to $\alpha$-divergence, which includes the special cases of Kullback-Leibler divergence, Hellinger distance and $\chi^2$ divergence. The…

统计理论 · 数学 2017-09-12 Yo Sheena

In previous work the authors defined the k-th order simplicial distance between probability distributions which arises naturally from a measure of dispersion based on the squared volume of random simplices of dimension k. This theory is…

统计理论 · 数学 2018-09-06 Luc Pronzato , Henry Wynn , Anatoly Zhigljavsky

This paper develops new limit theory for data that are generated by networks or more generally display cross-sectional dependence structures that are governed by observable and unobservable characteristics. Strategic network formation…

概率论 · 数学 2019-08-08 Guido M. Kuersteiner

We apply a suitable modification of the functional delta method to statistical functionals that arise from law-invariant coherent risk measures. To this end we establish differentiability of the statistical functional in a relaxed Hadamard…

统计理论 · 数学 2015-02-18 Volker Krätschmer , Alexander Schied , Henryk Zähle

Many machine learning models appear to deploy effortlessly under distribution shift, and perform well on a target distribution that is considerably different from the training distribution. Yet, learning theory of distribution shift bounds…

机器学习 · 计算机科学 2024-05-30 Robi Bhattacharjee , Nick Rittler , Kamalika Chaudhuri

In this paper we provide the asymptotic theory of the general of $\phi$-divergences measures, which include the most common divergence measures : Renyi and Tsallis families and the Kullback-Leibler measure. We are interested in divergence…

统计理论 · 数学 2019-04-01 Ba Amadou Diadie , Gane Samb Lo

Extreme Value Theory plays an important role to provide approximation results for the extremes of a sequence of independent random variables when their distribution is unknown. An important one is given by the {generalised Pareto…

概率论 · 数学 2024-05-08 Simone A. Padoan , Stefano Rizzelli