中文
相关论文

相关论文: Pointwise Convergence Analysis for Approximations …

200 篇论文

We study optimal mass transport problems between two measures with respect to a non-traditional cost function, i.e. a cost $c$ which can attain the value $+\infty$. We define the notion of $c$-compatibility and strong-$c$-compatibility of…

度量几何 · 数学 2021-07-09 Shiri Artstein-Avidan , Shay Sadovsky , Katarzyna Wyczesany

The inverse optimal transport problem is to find the underlying cost function from the knowledge of optimal transport plans. While this amounts to solving a linear inverse problem, in this work we will be concerned with the nonlinear…

最优化与控制 · 数学 2025-09-03 Alberto González-Sanz , Michel Groppe , Axel Munk

We propose a simple subsampling scheme for fast randomized approximate computation of optimal transport distances. This scheme operates on a random subset of the full data and can use any exact algorithm as a black-box back-end, including…

统计计算 · 统计学 2020-12-17 Max Sommerfeld , Jörn Schrieber , Yoav Zemel , Axel Munk

The Monge-Kantorovich problem is revisited by means of a variant of the saddle-point method without appealing to $c$-conjugates. A new abstract characterization of the optimal plans is obtained in the case where the cost function takes…

概率论 · 数学 2013-08-02 Christian Léonard

In compact settings, the convergence rate of the empirical optimal transport cost to its population value is well understood for a wide class of spaces and cost functions. In unbounded settings, however, hitherto available results require…

统计理论 · 数学 2024-07-24 Thomas Staudt , Shayan Hundrieser

Unbalanced optimal transport (UOT) extends classical optimal transport to measures with different total masses, but statistical guarantees for Monge-type estimation remain limited. We study unbalanced transport with quadratic cost and…

统计理论 · 数学 2026-05-12 Donlapark Ponnoprat , Noboru Isobe , Masaaki Imaizumi

The use of distances based on optimal transportation has recently shown promise for discrimination of power spectra. In particular, spectral estimation methods based on l1 regularization as well as covariance based methods can be shown to…

计算机视觉与模式识别 · 计算机科学 2019-04-09 Ali Sadeghian , Deoksu Lim , Johan Karlsson , Jian Li

We give a necessary and sufficient condition on the cost function so that the map solution of Monge's optimal transportation problem is continuous for arbitrary smooth positive data. This condition was first introduced by Ma, Trudinger and…

偏微分方程分析 · 数学 2013-01-29 G. Loeper

We investigate metric conditions that allow to prove existence and uniqueness of a map solving the Monge problem between two marginals in a metric (measure) space, proving two main results. Firstly, we introduce a nonsmooth version of the…

度量几何 · 数学 2024-10-31 Shucheng Li , Mattia Magnabosco , Timo Schultz

The optimal (Monge-Kantorovich) transportation problem is discussed from several points of view. The Lagrangian formulation extends the action of the {\em Lagrangian} $L(v,x,t)$ from the set of orbits in $\R^n$ to a set of measure-valued…

数学物理 · 物理学 2007-05-23 Gershon Wolansky

Matching on covariates is a well-established framework for estimating causal effects in observational studies. The principal challenge stems from the often high-dimensional structure of the problem. Many methods have been introduced to…

统计方法学 · 统计学 2022-07-12 Florian Gunsilius , Yuliang Xu

We employ scoring functions, used in statistics for eliciting risk functionals, as cost functions in the Monge-Kantorovich (MK) optimal transport problem. This gives raise to a rich variety of novel asymmetric MK divergences, which subsume…

风险管理 · 定量金融 2024-04-11 Silvana M. Pesenti , Steven Vanduffel

We study the multi-marginal partial optimal transport (POT) problem between $m$ discrete (unbalanced) measures with at most $n$ supports. We first prove that we can obtain two equivalence forms of the multimarginal POT problem in terms of…

机器学习 · 统计学 2022-02-25 Khang Le , Huy Nguyen , Tung Pham , Nhat Ho

A probabilistic method for solving the Monge-Kantorovich mass transport problem on $R^d$ is introduced. A system of empirical measures of independent particles is built in such a way that it obeys a doubly indexed large deviation principle…

概率论 · 数学 2007-10-09 Christian Léonard

We address the Monge problem in metric spaces with a geodesic distance: (X, d) is a Polish space and dN is a geodesic Borel distance which makes (X,dN) a possibly branching geodesic space. We show that under some assumptions on the…

概率论 · 数学 2012-10-01 Fabio Cavalletti

We propose a numerical method to find the optimal transport map between a measure supported on a lower-dimensional subset of R^d and a finitely supported measure. More precisely, the source measure is assumed to be supported on a simplex…

计算几何 · 计算机科学 2017-07-06 Quentin Mérigot , Jocelyn Meyron , Boris Thibert

We show that the discrete Sinkhorn algorithm - as applied in the setting of Optimal Transport on a compact manifold - converges to the solution of a fully non-linear parabolic PDE of Monge-Ampere type, in a large-scale limit. The latter…

偏微分方程分析 · 数学 2020-06-29 Robert J. Berman

This paper introduces a novel neural network-based approach to solving the Monge-Amp\`ere equation with the transport boundary condition, specifically targeted towards optical design applications. We leverage multilayer perceptron networks…

机器学习 · 计算机科学 2024-10-28 Roel Hacking , Lisa Kusch , Koondanibha Mitra , Martijn Anthonissen , Wilbert IJzerman

We consider Monge-Kantorovich optimal transport problems on $\mathbb{R}^d$, $d\ge 1$, with a convex cost function given by the cumulant generating function of a probability measure. Examples include the Wasserstein-2 transport whose cost…

概率论 · 数学 2017-08-29 Soumik Pal

We introduce a constrained optimal transport problem where origins $x$ can only be transported to destinations $y\geq x$. Our statistical motivation is to describe the sharp upper bound for the variance of the treatment effect $Y-X$ given…

最优化与控制 · 数学 2021-06-22 Marcel Nutz , Ruodu Wang