中文
相关论文

相关论文: Sup-sums principles for F-divergence, Kullback--Le…

200 篇论文

Integration at a point is a new kind of integration derived from integration over an interval in infinitesimal and infinity domains which are spaces larger than the reals. Consider a continuous monotonic divergent function that is…

综合数学 · 数学 2015-03-04 Chelton D. Evans , William K. Pattinson

As a continuation of the paper [20] on standard $f$-divergences, we make a systematic study of maximal $f$-divergences in general von Neumann algebras. For maximal $f$-divergences, apart from their definition based on Haagerup's…

数学物理 · 物理学 2019-02-20 Fumio Hiai

We consider the problem of estimating probability density functions based on sample data, using a finite mixture of densities from some component class. To this end, we introduce the $h$-lifted Kullback--Leibler (KL) divergence as a…

机器学习 · 统计学 2024-12-24 Mark Chiu Chong , Hien Duy Nguyen , TrungTin Nguyen

We consider Bayesian linear inverse problems in infinite-dimensional separable Hilbert spaces, with a Gaussian prior measure and additive Gaussian noise model, and provide an extension of the concept of Bayesian D-optimality to the…

统计理论 · 数学 2014-09-04 Alen Alexanderian , Philip Gloor , Omar Ghattas

We derive an optimal bound on the sum of entropic uncertainties of two or more observables when they are sequentially measured on the same ensemble of systems. This optimal bound is shown to be greater than or equal to the bounds derived in…

量子物理 · 物理学 2009-11-07 M. D. Srinivas

Most quantum divergences derive their structure from classical f-divergences or Renyi-type constructions, a dependence that obscures several quantum geometric effects. We introduce a quantum relative-alpha-entropy that extends Umegaki's…

量子物理 · 物理学 2026-04-09 Sayantan Roy , Atin Gayen , Aditi Kar Gangopadhyay , Sugata Gangopadhyay

In this note, with the help of the boundary classification of diffusions, we derive a criterion of the convergence of perpetual integral functionals of transient real-valued diffusions. In the particular case of transient Bessel processes,…

概率论 · 数学 2007-05-23 Paavo Salminen , Marc Yor

New upper bounds on the relative entropy are derived as a function of the total variation distance. One bound refines an inequality by Verd\'{u} for general probability measures. A second bound improves the tightness of an inequality by…

信息论 · 计算机科学 2015-04-14 Igal Sason

We present new counterexamples, which provide stronger limitations to sums-differences statements than were previously known. The main idea is to consider non-uniform probability measures.

组合数学 · 数学 2014-10-06 Marius Lemm

The Fokker-Planck equation can be reformulated as a continuity equation, which naturally suggests using the associated velocity field in particle flow methods. While the resulting probability flow ODE offers appealing properties - such as…

机器学习 · 统计学 2024-10-28 Ilja Klebanov

We define a general notion of entropy in elementary, algebraic terms. Based on that, weak forms of a scalar product and a distance measure are derived. We give basic properties of these quantities, generalize the Cauchy-Schwarz inequality,…

谱理论 · 数学 2024-04-10 Martin Schlather

The necessary information to distinguish a local inhomogeneous mass density field from its spatial average on a compact domain of the universe can be measured by relative information entropy. The Kullback-Leibler (KL) formula arises very…

广义相对论与量子宇宙学 · 物理学 2016-04-28 Viktor G. Czinner , Filipe C. Mena

Entropy-like functionals on operator algebras have been studied since the pioneering work of von Neumann, Umegaki, Lindblad, and Lieb. The most well-known are the von Neumann entropy $trace (\rho\log \rho)$ and a generalization of the…

最优化与控制 · 数学 2008-07-19 Tryphon T. Georgiou

The logistic loss (a.k.a. cross-entropy loss) is one of the most popular loss functions used for multiclass classification. It is also the loss function of choice for next-token prediction in language modeling. It is associated with the…

机器学习 · 计算机科学 2025-06-16 Vincent Roulet , Tianlin Liu , Nino Vieillard , Michael E. Sander , Mathieu Blondel

Good robust estimators can be tuned to combine a high breakdown point and a specified asymptotic efficiency at a central model. This happens in regression with MM- and tau-estimators among others. However, the finite-sample efficiency of…

统计理论 · 数学 2013-11-21 Ricardo Maronna , Víctor Yohai

Furstenberg has associated to every topological group $G$ a universal boundary $\partial(G)$. If we consider in addition a subgroup $H<G$, the relative notion of $(G,H)$-boundaries admits again a maximal object $\partial(G,H)$. In the case…

动力系统 · 数学 2020-12-23 Nicolas Monod

This paper extends some geometric properties of a one-parameter family of relative entropies. These arise as redundancies when cumulants of compressed lengths are considered instead of expected compressed lengths. These parametric relative…

信息论 · 计算机科学 2011-05-31 Ashok Kumar M. , Rajesh Sundaresan

$f$-divergences, which quantify discrepancy between probability distributions, are ubiquitous in information theory, machine learning, and statistics. While there are numerous methods for estimating $f$-divergences from data, a limit…

统计理论 · 数学 2023-10-13 Sreejith Sreekumar , Ziv Goldfeld , Kengo Kato

Let $(X,T)$ be a topological dynamical system. We define the measure-theoretical lower and upper entropies $\underline{h}_\mu(T)$, $\bar{h}_\mu(T)$ for any $\mu\in M(X)$, where $M(X)$ denotes the collection of all Borel probability measures…

动力系统 · 数学 2010-12-07 De-Jun Feng , Wen Huang

We give conditions on a finitary endofunctor of a finitely accessible category to admit a final coalgebra. Our conditions always apply to the case of a finitary endofunctor of a locally finitely presentable (l.f.p.) category and they bring…

范畴论 · 数学 2009-06-01 Panagis Karazeris , Apostolos Matzaris , Jiri Velebil