中文
相关论文

相关论文: Pseudo-Riemannian geometry embeds information geom…

200 篇论文

Optimal transport is a powerful framework for computing distances between probability distributions. We unify the two main approaches to optimal transport, namely Monge-Kantorovitch and Sinkhorn-Cuturi, into what we define as Tsallis…

机器学习 · 计算机科学 2016-09-16 Boris Muzellec , Richard Nock , Giorgio Patrini , Frank Nielsen

We present a novel framework based on optimal transport for the challenging problem of comparing graphs. Specifically, we exploit the probabilistic distribution of smooth graph signals defined with respect to the graph topology. This allows…

机器学习 · 计算机科学 2019-12-09 Hermina Petric Maretic , Mireille EL Gheche , Giovanni Chierchia , Pascal Frossard

In Riemannian geometry geodesics are integral curves of the Riemannian distance gradient. We extend this classical result to the framework of Information Geometry. In particular, we prove that the rays of level-sets defined by a…

微分几何 · 数学 2021-06-30 Domenico Felice , Nihat Ay

The optimal transport (OT) map is a geometry-driven transformation between high-dimensional probability distributions which underpins a wide range of tasks in statistics, applied probability, and machine learning. However, existing…

机器学习 · 统计学 2025-12-11 Sloan Nietert , Ziv Goldfeld

Information geometry is concerned with the application of differential geometry concepts in the study of the parametric spaces of statistical models. When the random variables are independent and identically distributed, the underlying…

信息论 · 计算机科学 2021-10-05 Alexandre L. M. Levada

Starting from a general $N$-band Hamiltonian with weak spatial and temporal variations, we derive a low energy effective theory for transport within one or several overlapping bands. To this end, we use the Wigner representation that allows…

介观与纳米尺度物理 · 物理学 2013-08-09 Christian Wickles , Wolfgang Belzig

The Gromov-Wasserstein (GW) distance, rooted in optimal transport (OT) theory, quantifies dissimilarity between metric measure spaces and provides a framework for aligning heterogeneous datasets. While computational aspects of the GW…

统计理论 · 数学 2023-10-02 Zhengxin Zhang , Ziv Goldfeld , Youssef Mroueh , Bharath K. Sriperumbudur

We prove quantitative bounds on the stability of optimal transport maps and Kantorovich potentials from a fixed source measure $\rho$ under variations of the target measure $\mu$, when the cost function is the squared Riemannian distance on…

度量几何 · 数学 2025-05-06 Jun Kitagawa , Cyril Letrouit , Quentin Mérigot

Multi-marginal optimal transport enables one to compare multiple probability measures, which increasingly finds application in multi-task learning problems. One practical limitation of multi-marginal transport is computational scalability…

We introduce a new paradigm, $\textit{measure synchronization}$, for synchronizing graphs with measure-valued edges. We formulate this problem as maximization of the cycle-consistency in the space of probability measures over relative…

计算机视觉与模式识别 · 计算机科学 2020-04-03 Tolga Birdal , Michael Arbel , Umut Şimşekli , Leonidas Guibas

We introduce an optimal transport-based model for learning a metric tensor from cross-sectional samples of evolving probability measures on a common Riemannian manifold. We neurally parametrize the metric as a spatially-varying matrix field…

机器学习 · 计算机科学 2023-03-08 Christopher Scarvelis , Justin Solomon

Using the square-root map p-->\sqrt{p} a probability density function p can be represented as a point of the unit sphere S in the Hilbert space of square-integrable functions. If the density function depends smoothly on a set of parameters,…

统计力学 · 物理学 2009-12-31 Dorje C. Brody , Daniel W. Hook

We define a novel class of distances between statistical multivariate distributions by modeling an optimal transport problem on their marginals with respect to a ground distance defined on their conditionals. These new distances are metrics…

机器学习 · 计算机科学 2020-11-03 Frank Nielsen , Ke Sun

This paper is concerned with the study of the Monge optimal transport problem in sub-Riemannian manifolds where the cost is given by the square of the sub-Riemannian distance. Our aim is to extend previous results on existence and…

微分几何 · 数学 2017-06-23 Zeinab Badreddine

Information geometry and Wasserstein geometry are two main structures introduced in a manifold of probability distributions, and they capture its different characteristics. We study characteristics of Wasserstein geometry in the framework…

统计理论 · 数学 2024-06-26 Shun-ichi Amari , Takeru Matsuda

The purpose of this paper is to employ the language of Cartan moving frames to study the geometry of the data manifolds and its Riemannian structure, via the data information metric and its curvature at data points. Using this framework and…

机器学习 · 统计学 2024-11-21 Eliot Tron , Rita Fioresi , Nicolas Couellan , Stéphane Puechmorel

We propose a technique for interpolating between probability distributions on discrete surfaces, based on the theory of optimal transport. Unlike previous attempts that use linear programming, our method is based on a dynamical formulation…

偏微分方程分析 · 数学 2018-09-20 Hugo Lavenant , Sebastian Claici , Edward Chien , Justin Solomon

Classic optimal transport theory is formulated through minimizing the expected transport cost between two given distributions. We propose the framework of distorted optimal transport by minimizing a distorted expected cost, which is the…

最优化与控制 · 数学 2025-05-20 Haiyan Liu , Bin Wang , Ruodu Wang , Sheng Chao Zhuang

The branched transport problem, a popular recent variant of optimal transport, is a non-convex and non-smooth variational problem on Radon measures. The so-called urban planning problem, on the contrary, is a shape optimization problem that…

最优化与控制 · 数学 2022-06-15 Julius Lohmann , Bernhard Schmitzer , Benedikt Wirth

In many statistical settings, two types of data are available: coupled data, which preserve the joint structure among variables but are limited in size due to cost or privacy constraints, and marginal data, which are available at larger…

统计方法学 · 统计学 2026-03-31 Jakwang Kim , Young-Heon Kim , Chan Park