中文
相关论文

相关论文: On $w$-mixtures: Finite convex combinations of pre…

200 篇论文

Exponential families and mixture families are parametric probability models that can be geometrically studied as smooth statistical manifolds with respect to any statistical divergence like the Kullback-Leibler (KL) divergence or the…

机器学习 · 计算机科学 2018-03-21 Frank Nielsen , Gaëtan Hadjeres

We study Bregman divergences in probability density space embedded with the $L^2$-Wasserstein metric. Several properties and dualities of transport Bregman divergences are provided. In particular, we derive the transport Kullback-Leibler…

信息论 · 计算机科学 2025-04-08 Wuchen Li

A smooth and strictly convex function on an open convex domain induces both (1) a Hessian manifold with respect to the standard flat Euclidean connection, and (2) a dually flat space of information geometry. We first review these…

信息论 · 计算机科学 2022-01-07 Frank Nielsen

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

We study the Kullback--Leibler (KL) divergence approximation theory of Gaussian mixture models (GMMs) by isolating an abstract mechanism behind several necessary-and-sufficient statements. The necessity direction is universal: if a density…

统计理论 · 数学 2026-04-14 Hien Duy Nguyen

Construction of ambiguity set in robust optimization relies on the choice of divergences between probability distributions. In distribution learning, choosing appropriate probability distributions based on observed data is critical for…

机器学习 · 统计学 2017-05-24 Xin Guo , Johnny Hong , Nan Yang

Mixture distributions are extensively used as a modeling tool in diverse areas from machine learning to communications engineering to physics, and obtaining bounds on the entropy of probability distributions is of fundamental importance in…

信息论 · 计算机科学 2022-12-05 James Melbourne , Saurav Talukdar , Shreyas Bhaban , Mokshay Madiman , Murti V. Salapaka

In this paper, we study the statistical and geometrical properties of the Kullback-Leibler divergence with kernel covariance operators (KKL) introduced by Bach [2022]. Unlike the classical Kullback-Leibler (KL) divergence that involves…

机器学习 · 统计学 2025-03-12 Clémentine Chazal , Anna Korba , Francis Bach

We first introduce the class of strictly quasiconvex and strictly quasiconcave Jensen divergences which are oriented (asymmetric) distances, and study some of their properties. We then define the strictly quasiconvex Bregman divergences as…

信息论 · 计算机科学 2019-10-08 Frank Nielsen , Gaëtan Hadjeres

Score-matching generative models have proven successful at sampling from complex high-dimensional data distributions. In many applications, this distribution is believed to concentrate on a much lower $d$-dimensional manifold embedded into…

机器学习 · 统计学 2025-04-25 Peter Potaptchik , Iskander Azangulov , George Deligiannidis

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

We derive relations between theoretical properties of restricted Boltzmann machines (RBMs), popular machine learning models which form the building blocks of deep learning models, and several natural notions from discrete mathematics and…

机器学习 · 统计学 2014-09-22 Guido F. Montufar , Jason Morton

Many natural and social science systems are described using probability distributions over elements that are related to each other: for instance, occupations with shared skills or species with similar traits. Standard information theory…

信息论 · 计算机科学 2026-03-24 Rohit Sahasrabuddhe , Renaud Lambiotte

We study quasi-Newton methods from the viewpoint of information geometry induced associated with Bregman divergences. Fletcher has studied a variational problem which derives the approximate Hessian update formula of the quasi-Newton…

统计计算 · 统计学 2010-10-15 Takafumi Kanamori , Atsumi Ohara

We propose a greedy mixture reduction algorithm which is capable of pruning mixture components as well as merging them based on the Kullback-Leibler divergence (KLD). The algorithm is distinct from the well-known Runnalls' KLD based method…

机器学习 · 统计学 2015-08-25 Tohid Ardeshiri , Umut Orguner , Emre Özkan

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

The Jensen-Shannon divergence is a renown bounded symmetrization of the unbounded Kullback-Leibler divergence which measures the total Kullback-Leibler divergence to the average mixture distribution. However the Jensen-Shannon divergence…

信息论 · 计算机科学 2022-09-21 Frank Nielsen

This paper shows that large nonparametric classes of conditional multivariate densities can be approximated in the Kullback--Leibler distance by different specifications of finite mixtures of normal regressions in which normal means and…

统计理论 · 数学 2010-10-05 Andriy Norets

In this paper, we develop a finite mixture of convolutional distributions, a statistical model to analyze continuous data distributed approximately on a mixture of low-dimensional affine subspaces. The observations are assumed independent…

统计理论 · 数学 2026-04-21 Sunrit Chakraborty , XuanLong Nguyen

The Jensen-Shannon divergence is a renown bounded symmetrization of the Kullback-Leibler divergence which does not require probability densities to have matching supports. In this paper, we introduce a vector-skew generalization of the…

信息论 · 计算机科学 2020-10-01 Frank Nielsen
‹ 上一页 1 2 3 10 下一页 ›