English
Related papers

Related papers: Necessary optimality conditions for geodesics in w…

200 papers

Wasserstein distances are metrics on probability distributions inspired by the problem of optimal mass transportation. Roughly speaking, they measure the minimal effort required to reconfigure the probability mass of one distribution in…

Methodology · Statistics 2019-04-10 Victor M. Panaretos , Yoav Zemel

On a closed Riemannian manifold, we construct a family of intrinsic Gaussian noises indexed by a regularity parameter $\alpha\geq0$ to study the well-posedness of the parabolic Anderson model. We show that with rough initial conditions, the…

Probability · Mathematics 2025-12-17 Hongyi Chen , Cheng Ouyang

We consider $L^2$ minimizing geodesics along the group of volume preserving maps $SDiff(D)$ of a given 3-dimensional domain $D$. The corresponding curves describe the motion of an ideal incompressible fluid inside $D$ and are (formally)…

Analysis of PDEs · Mathematics 2010-11-05 Yann Brenier

Wasserstein balls, which contain all probability measures within a pre-specified Wasserstein distance to a reference measure, have recently enjoyed wide popularity in the distributionally robust optimization and machine learning communities…

Optimization and Control · Mathematics 2021-06-08 Man-Chung Yue , Daniel Kuhn , Wolfram Wiesemann

The equations of motion of a charged ideal fluid, respectively the superconductivity equation (both in a given magnetic field) are showed to be geodesic equations on a general, respectively central extension of the group of volume…

Differential Geometry · Mathematics 2009-11-07 Cornelia Vizman

We construct geodesics in the Wasserstein space of probability measure along which all the measures have an upper bound on their density that is determined by the densities of the endpoints of the geodesic. Using these geodesics we show…

Differential Geometry · Mathematics 2011-11-24 Tapio Rajala

Inverse problems in physical or biological sciences often involve recovering an unknown parameter that is random. The sought-after quantity is a probability distribution of the unknown parameter, that produces data that aligns with…

Machine Learning · Statistics 2024-10-02 Qin Li , Maria Oprea , Li Wang , Yunan Yang

Wasserstein barycenters define averages of probability measures in a geometrically meaningful way. Their use is increasingly popular in applied fields, such as image, geometry or language processing. In these fields however, the probability…

Numerical Analysis · Mathematics 2023-03-13 Guillaume Carlier , Alex Delalande , Quentin Merigot

We study metric projections onto cones in the Wasserstein space of probability measures, defined by stochastic orders. Dualities for backward and forward projections are established under general conditions. Dual optimal solutions and their…

Probability · Mathematics 2021-10-12 Young-Heon Kim , Yuan Long Ruan

We consider the fundamental task of optimising a real-valued function defined in a potentially high-dimensional Euclidean space, such as the loss function in many machine-learning tasks or the logarithm of the probability distribution in…

Machine Learning · Statistics 2024-03-20 Marcelo Hartmann , Bernardo Williams , Hanlin Yu , Mark Girolami , Alessandro Barp , Arto Klami

We analyze a non-standard isoperimetric problem in the plane associated with a metric having degenerate conformal factor at two points. Under certain assumptions on the conformal factor, we establish the existence of curves of least length…

Analysis of PDEs · Mathematics 2015-09-15 Stan Alama , Lia Bronsard , Andres Contreras , Jiri Dadok , Peter Sternberg

Wasserstein distance induces a natural Riemannian structure for the probabilities on the Euclidean space. This insight of classical transport theory is fundamental for tremendous applications in various fields of pure and applied…

Probability · Mathematics 2023-08-14 Daniel Bartl , Mathias Beiglböck , Gudmund Pammer

We develop a notion of projections between sets of probability measures using the geometric properties of the 2-Wasserstein space. It is designed for general multivariate probability measures, is computationally efficient to implement, and…

Machine Learning · Statistics 2022-08-04 Florian Gunsilius , Meng Hsuan Hsieh , Myung Jin Lee

Probabilistic frames are a generalization of finite frames into the Wasserstein space of probability measures with finite second moment. We introduce new probabilistic definitions of duality, analysis, and synthesis and investigate their…

Functional Analysis · Mathematics 2017-05-03 Clare Wickman , Kasso Okoudjou

We investigate here the optimal transportation problem on configuration space for the quadratic cost. It is shown that, as usual, provided that the corresponding Wasserstein is finite, there exists one unique optimal measure and that this…

Probability · Mathematics 2007-05-23 L. Decreusefond

This paper is concerned by statistical inference problems from a data set whose elements may be modeled as random probability measures such as multiple histograms or point clouds. We propose to review recent contributions in statistics on…

Statistics Theory · Mathematics 2019-08-27 Jérémie Bigot

The Busemann function has recently found much interest in a variety of geometric machine learning problems, as it naturally defines projections onto geodesic rays of Riemannian manifolds and generalizes the notion of hyperplanes. As several…

Machine Learning · Computer Science 2026-03-13 Clément Bonet , Elsa Cazelles , Lucas Drumetz , Nicolas Courty

In this paper, we investigate the well-posedness of the martingale problem associated to non-linear stochastic differential equations (SDEs) in the sense of McKean-Vlasov under mild assumptions on the coefficients as well as classical…

Classical Analysis and ODEs · Mathematics 2021-04-23 Paul-Eric Chaudru de Raynal , Noufel Frikha

We study existence of probability measure valued jump-diffusions described by martingale problems. We develop a simple device that allows us to embed Wasserstein spaces and other similar spaces of probability measures into locally compact…

Probability · Mathematics 2020-12-03 Martin Larsson , Sara Svaluto-Ferro

This work is concerned with the quantification of the epistemic uncertainties induced the discretization of partial differential equations. Following the paradigm of probabilistic numerics, we quantify this uncertainty probabilistically.…

Probability · Mathematics 2016-07-14 Ilias Bilionis