中文
相关论文

相关论文: A geometric study of Wasserstein spaces: Hadamard …

200 篇论文

Given a metric space X, one defines its Wasserstein space W2(X) as a set of sufficiently decaying probability measures on X endowed with a metric defined from optimal transportation. In this article, we continue the geometric study of W2(X)…

度量几何 · 数学 2019-10-15 Jérôme Bertrand , Benoît Kloeckner

The aim of this short paper is to offer a complete characterization of all (not necessarily surjective) isometric embeddings of the Wasserstein space $\mathcal{W}_p(\mathcal{X})$, where $\mathcal{X}$ is a countable discrete metric space and…

泛函分析 · 数学 2019-08-23 György Pál Gehér , Tamás Titkos , Dániel Virosztek

The sliced Wasserstein metric compares probability measures on $\mathbb{R}^d$ by taking averages of the Wasserstein distances between projections of the measures to lines. The distance has found a range of applications in statistics and…

偏微分方程分析 · 数学 2024-11-25 Sangmin Park , Dejan Slepčev

Let $(X,d,\mathfrak{m})$ be a metric measure space. The study of the Wasserstein space $(\mathbb{P}_p(X),\mathbb{W}_p)$ associated to $X$ has proved useful in describing several geometrical properties of $X.$ In this paper we focus on the…

度量几何 · 数学 2021-02-18 Jaime Santos-Rodríguez

Given a family of probability measures in P(X), the space of probability measures on a Hilbert space X, our goal in this paper is to highlight one ore more curves in P(X) that summarize efficiently that family. We propose to study this…

机器学习 · 统计学 2015-11-24 Vivien Seguy , Marco Cuturi

In this paper we investigate properties of metric projections onto specific closed and geodesically convex proper subsets of Wasserstein spaces $(\mathcal{P}_p(\mathbf{R}^d),W_p).$ When $d=1$, as $(\mathcal{P}_2(\mathbf{R}),W_2)$ is…

泛函分析 · 数学 2025-09-03 Anshul Adve , Alpár Mészáros

We extend the geometric study of the Wasserstein space W(X) of a simply connected, negatively curved metric space X by investigating which pairs of boundary points can be linked by a geodesic, when X is a tree.

微分几何 · 数学 2013-05-14 Jérôme Bertrand , Benoit Kloeckner

We study the geometry of the space of measures of a compact ultrametric space X, endowed with the L^p Wasserstein distance from optimal transportation. We show that the power p of this distance makes this Wasserstein space affinely…

泛函分析 · 数学 2014-06-04 Benoît Kloeckner

We investigate the stability of the Wasserstein distance, a metric structure on the space of probability measures arising from the theory of optimal transport, under metric ultralimits. We first show that if $(X_{i},d_{i})_{i\in\mathbb{N}}$…

度量几何 · 数学 2023-03-09 Andrew Warren

Wasserstein distance, especially among symmetric positive-definite matrices, has broad and deep influences on development of artificial intelligence (AI) and other branches of computer science. A natural idea is to describe the geometry of…

微分几何 · 数学 2021-05-12 Yihao Luo , Shiqiang Zhang , Yueqi Cao , Huafei Sun

Our purpose in this paper is to study isometries and isometric embeddings of the $p$-Wasserstein space $\mathcal{W}_p(\mathbb{H}^n)$ over the Heisenberg group $\mathbb{H}^n$ for all $p>1$ and for all $n\geq 1$. First, we create a link…

度量几何 · 数学 2025-10-07 Zoltán M. Balogh , Tamás Titkos , Dániel Virosztek

The space of Gaussian measures on a Euclidean space is geodesically convex in the $L^2$-Wasserstein space. This space is a finite dimensional manifold since Gaussian measures are parameterized by means and covariance matrices. By…

微分几何 · 数学 2009-02-11 Asuka Takatsu

We study the reach (in the sense of Federer) of the natural isometric embedding $X\hookrightarrow W_p(X)$ of $X$ inside its $p$-Wasserstein space, where $(X,\operatorname{dist})$ is a geodesic metric space. We prove that if a point $x\in X$…

度量几何 · 数学 2023-07-04 Javier Casado , Manuel Cuerno , Jaime Santos-Rodríguez

While many Machine Learning methods were developed or transposed on Riemannian manifolds to tackle data with known non Euclidean geometry, Optimal Transport (OT) methods on such spaces have not received much attention. The main OT tool on…

机器学习 · 计算机科学 2024-03-12 Clément Bonet , Lucas Drumetz , Nicolas Courty

Euclidean embeddings of data are fundamentally limited in their ability to capture latent semantic structures, which need not conform to Euclidean spatial assumptions. Here we consider an alternative, which embeds data as discrete…

机器学习 · 计算机科学 2019-05-10 Charlie Frogner , Farzaneh Mirzazadeh , Justin Solomon

We study geodesically complete and locally compact Hadamard spaces X whose Tits boundary is a connected irreducible spherical building. We show that X is symmetric iff complete geodesics in X do not branch and a Euclidean building…

度量几何 · 数学 2009-03-04 Bernhard Leeb

We introduce the observable Wasserstein distance, a framework for deriving lower bounds on the Wasserstein distance between probability measures on Polish metric spaces, designed to bypass the computational intractability of exact optimal…

We study the Wasserstein space (with quadratic cost) of Euclidean spaces as an intrinsic metric space. In particular we compute their isometry groups. Surprisingly, in the case of the line, there exists a (unique) "exotic" isometric flow.…

度量几何 · 数学 2010-06-24 Benoit Kloeckner

In this paper, we study isometries of $p$-Wasserstein spaces. In our first result, for every complete and separable metric space $X$ and for every $p\geq1$, we construct a metric space $Y$ such that $X$ embeds isometrically into $Y$, and…

度量几何 · 数学 2025-10-20 Zoltán M. Balogh , Eric Ströher , Tamás Titkos , Dániel Virosztek

In this essay, we discuss the notion of optimal transport on geodesic measure spaces and the associated (2-)Wasserstein distance. We then examine displacement convexity of the entropy functional on the space of probability measures. In…

度量几何 · 数学 2012-04-17 Otis Chodosh
‹ 上一页 1 2 3 10 下一页 ›