中文
相关论文

相关论文: Logarithmic divergences from optimal transport and…

200 篇论文

We study the logarithmic $L^{(\alpha)}$-divergence which extrapolates the Bregman divergence and corresponds to solutions to novel optimal transport problems. We show that this logarithmic divergence is equivalent to a conformal…

微分几何 · 数学 2019-06-24 Ting-Kam Leonard Wong , Jiaowen Yang

In information geometry, generalized exponential families and statistical manifolds with curvature are under active investigation in recent years. In this paper we consider the statistical manifold induced by a logarithmic…

微分几何 · 数学 2021-05-18 Zhixu Tao , Ting-Kam Leonard Wong

In the field of statistics, many kind of divergence functions have been studied as an amount which measures the discrepancy between two probability distributions. In the differential geometrical approach in statistics (information…

统计方法学 · 统计学 2018-09-11 Tomohiro Nishiyama

A function is exponentially concave if its exponential is concave. We consider exponentially concave functions on the unit simplex. In a previous paper we showed that gradient maps of exponentially concave functions provide solutions to a…

概率论 · 数学 2017-06-01 Soumik Pal , Ting-Kam Leonard Wong

The logarithmic divergence is an extension of the Bregman divergence motivated by optimal transport and a generalized convex duality, and satisfies many remarkable properties. Using the geometry induced by the logarithmic divergence, we…

最优化与控制 · 数学 2022-09-08 Amanjit Singh Kainth , Ting-Kam Leonard Wong , Frank Rudzicz

We propose a new family of regularized R\'enyi divergences parametrized not only by the order $\alpha$ but also by a variational function space. These new objects are defined by taking the infimal convolution of the standard R\'enyi…

Exponential families are statistical models which are the workhorses in statistics, information theory, and machine learning among others. An exponential family can either be normalized subtractively by its cumulant or free energy function…

信息论 · 计算机科学 2024-02-27 Frank Nielsen

The Bregman-Wasserstein divergence is the optimal transport cost when the underlying cost function is given by a Bregman divergence, and arises naturally in fields such as statistics and machine learning. We establish fundamental properties…

概率论 · 数学 2025-04-14 Amanjit Singh Kainth , Cale Rankin , Ting-Kam Leonard Wong

A loss function measures the discrepancy between the true values and their estimated fits, for a given instance of data. In classification problems, a loss function is said to be proper if a minimizer of the expected loss is the true…

信息论 · 计算机科学 2020-01-03 Amichai Painsky , Gregory W. Wornell

The aim of this work is to establish that two recently published projection theorems, one dealing with a parametric generalization of relative entropy and another dealing with R\'{e}nyi divergence, are equivalent under a correspondence on…

信息论 · 计算机科学 2019-05-07 P. N. Karthik , Rajesh Sundaresan

Optimal transport and information geometry both study geometric structures on spaces of probability distributions. Optimal transport characterizes the cost-minimizing movement from one distribution to another, while information geometry…

微分几何 · 数学 2021-05-07 Ting-Kam Leonard Wong , Jiaowen Yang

Projection theorems of divergences enable us to find reverse projection of a divergence on a specific statistical model as a forward projection of the divergence on a different but rather "simpler" statistical model, which, in turn, results…

信息论 · 计算机科学 2017-06-19 Atin Gayen , M. Ashok Kumar

Divergence functions are interesting discrepancy measures. Even though they are not true distances, we can use them to measure how separated two points are. Curiously enough, when they are applied to random variables, they lead to a notion…

统计理论 · 数学 2018-09-21 Henryk Gzyl

This paper studies forward and reverse projections for the R\'{e}nyi divergence of order $\alpha \in (0, \infty)$ on $\alpha$-convex sets. The forward projection on such a set is motivated by some works of Tsallis {\em et al.} in…

信息论 · 计算机科学 2016-07-27 M. Ashok Kumar , Igal Sason

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

Many problems in machine learning can be formulated as optimizing a convex functional over a vector space of measures. This paper studies the convergence of the mirror descent algorithm in this infinite-dimensional setting. Defining Bregman…

最优化与控制 · 数学 2022-10-12 Pierre-Cyril Aubin-Frankowski , Anna Korba , Flavien Léger

Information geometry applies concepts in differential geometry to probability and statistics and is especially useful for parameter estimation in exponential families where parameters are known to lie on a Riemannian manifold. Connections…

机器学习 · 统计学 2014-05-01 Garvesh Raskutti , Sayan Mukherjee

Optimal transportation distances are valuable for comparing and analyzing probability distributions, but larger-scale computational techniques for the theoretically favorable quadratic case are limited to smooth domains or regularized…

其他计算机科学 · 计算机科学 2016-03-23 Justin Solomon , Raif Rustamov , Leonidas Guibas , Adrian Butscher

The Bregman divergence (Bregman distance, Bregman measure of distance) is a certain useful substitute for a distance, obtained from a well-chosen function (the "Bregman function"). Bregman functions and divergences have been extensively…

最优化与控制 · 数学 2019-04-10 Daniel Reem , Simeon Reich , Alvaro De Pierro

Regularized optimal transport (OT) has received much attention in recent years starting from Cuturi's introduction of Kullback-Leibler (KL) divergence regularized OT. In this paper, we propose regularizing the OT problem using the family of…

最优化与控制 · 数学 2025-10-28 Jonas Bresch , Viktor Stein
‹ 上一页 1 2 3 10 下一页 ›