English
Related papers

Related papers: Natural gradient via optimal transport

200 papers

The Bregman-Wasserstein divergence is the optimal transport cost when the underlying cost function is given by a Bregman divergence, and arises naturally in fields such as statistics and machine learning. We establish fundamental properties…

Probability · Mathematics 2025-04-14 Amanjit Singh Kainth , Cale Rankin , Ting-Kam Leonard Wong

This paper provides results on Wasserstein gradient flows between measures on the real line. Utilizing the isometric embedding of the Wasserstein space $\mathcal P_2(\mathbb R)$ into the Hilbert space $L_2((0,1))$, Wasserstein gradient…

Optimization and Control · Mathematics 2024-08-13 Johannes Hertrich , Robert Beinert , Manuel Gräf , Gabriele Steidl

The natural gradient field is a vector field that lives on a model equipped with a distinguished Riemannian metric, e.g. the Fisher-Rao metric, and represents the direction of steepest ascent of an objective function on the model with…

Machine Learning · Computer Science 2022-07-01 Jesse van Oostrum , Johannes Müller , Nihat Ay

Let $M$ be a connected compact Riemannian manifold possibly with a boundary, let $V\in C^2(M)$ such that $\mu(\d x):=\e^{V(x)}\d x$ is a probability measure, where $\d x$ is the volume measure, and let $L=\Delta+\nabla V$. The exact…

Probability · Mathematics 2021-07-27 Feng-Yu Wang , Bingyao Wu

We propose efficient numerical schemes for implementing the natural gradient descent (NGD) for a broad range of metric spaces with applications to PDE-based optimization problems. Our technique represents the natural gradient direction as a…

Optimization and Control · Mathematics 2023-01-12 Levon Nurbekyan , Wanzhou Lei , Yunan Yang

In this paper, we apply the framework of optimal transport to the formulation of optimal design problems. By considering the Wasserstein space as a set of design variables, we associate each probability measure with a shape configuration of…

Optimization and Control · Mathematics 2025-09-08 Fumiya Okazaki , Takayuki Yamada

The Wasserstein metric is an important measure of distance between probability distributions, with applications in machine learning, statistics, probability theory, and data analysis. This paper provides upper and lower bounds on…

Statistics Theory · Mathematics 2019-11-11 Shashank Singh , Barnabás Póczos

We present a novel method for efficiently computing optimal transport maps and Wasserstein barycenters in high-dimensional spaces. Our approach uses conditional normalizing flows to approximate the input distributions as invertible…

Machine Learning · Statistics 2025-05-29 Gabriele Visentin , Patrick Cheridito

The analysis of samples of random objects that do not lie in a vector space is gaining increasing attention in statistics. An important class of such object data is univariate probability measures defined on the real line. Adopting the…

Methodology · Statistics 2021-07-07 Yaqing Chen , Zhenhua Lin , Hans-Georg Müller

Estimating the density of a distribution from samples is a fundamental problem in statistics. In many practical settings, the Wasserstein distance is an appropriate error metric for density estimation. For example, when estimating…

Machine Learning · Computer Science 2024-07-01 Vitaly Feldman , Audra McMillan , Satchit Sivakumar , Kunal Talwar

We provide gradient flow interpretations for the continuous-time continuous-state Hopfield neural network (HNN). The ordinary and stochastic differential equations associated with the HNN were introduced in the literature as analog…

Optimization and Control · Mathematics 2019-11-15 Abhishek Halder , Kenneth F. Caluya , Bertrand Travacca , Scott J. Moura

Learning algorithms for implicit generative models can optimize a variety of criteria that measure how the data distribution differs from the implicit model distribution, including the Wasserstein distance, the Energy distance, and the…

Machine Learning · Statistics 2019-08-23 Leon Bottou , Martin Arjovsky , David Lopez-Paz , Maxime Oquab

The Wasserstein distance is a distance between two probability distributions and has recently gained increasing popularity in statistics and machine learning, owing to its attractive properties. One important approach to extending this…

Methodology · Statistics 2022-02-14 Ryo Okano , Masaaki Imaizumi

We provide a numerical analysis and computation of neural network projected schemes for approximating one dimensional Wasserstein gradient flows. We approximate the Lagrangian mapping functions of gradient flows by the class of two-layer…

Numerical Analysis · Mathematics 2024-02-27 Xinzhe Zuo , Jiaxi Zhao , Shu Liu , Stanley Osher , Wuchen Li

Flow matching has recently emerged as a flexible and efficient framework for generative modelling by learning deterministic transport dynamics between probability measures. In this work, we extend flow matching to the space of probability…

Machine Learning · Computer Science 2026-05-12 Moritz Piening , Richard Duong , Gabriele Steidl

Gromov--Wasserstein (GW) distances compare graphs, shapes, and point clouds through internal distances, without requiring a common coordinate system. This invariance is powerful, but discrete GW is a nonconvex quadratic optimal transport…

Machine Learning · Computer Science 2026-05-15 Ao Xu , Tieru Wu

We propose a mathematically principled PDE gradient flow framework for distributionally robust optimization (DRO). Exploiting the recent advances in the intersection of Markov Chain Monte Carlo sampling and gradient flow theory, we show…

Optimization and Control · Mathematics 2026-05-27 Zusen Xu , Jia-Jie Zhu

We present new algorithms to compute the mean of a set of empirical probability measures under the optimal transport metric. This mean, known as the Wasserstein barycenter, is the measure that minimizes the sum of its Wasserstein distances…

Machine Learning · Statistics 2014-06-18 Marco Cuturi , Arnaud Doucet

We present a novel approximate inference method for diffusion processes, based on the Wasserstein gradient flow formulation of the diffusion. In this formulation, the time-dependent density of the diffusion is derived as the limit of…

Machine Learning · Statistics 2018-06-13 Charlie Frogner , Tomaso Poggio

Wasserstein distributionally robust optimization offers a framework for model fitting in machine learning under potential shifts in the data distribution. We study a regularized variant of this problem in which entropic smoothing produces a…

Optimization and Control · Mathematics 2026-05-28 Tam Le