English
Related papers

Related papers: DOTmark - A Benchmark for Discrete Optimal Transpo…

200 papers

Optimal transport distances are powerful tools to compare probability distributions and have found many applications in machine learning. Yet their algorithmic complexity prevents their direct use on large scale datasets. To overcome this…

Machine Learning · Statistics 2021-10-14 Kilian Fatras , Younes Zine , Rémi Flamary , Rémi Gribonval , Nicolas Courty

We develop the theory of a metric, which we call the $\nu$-based Wasserstein metric and denote by $W_\nu$, on the set of probability measures $\mathcal P(X)$ on a domain $X \subseteq \mathbb{R}^m$. This metric is based on a slight…

Optimization and Control · Mathematics 2022-09-16 Luca Nenna , Brendan Pass

The theory of optimal transport of probability measures has wide-ranging applications across a number of different fields, including concentration of measure, machine learning, Markov chains, and economics. The generalisation of optimal…

Quantum Physics · Physics 2026-04-21 Emily Beatty

The notion of entropy-regularized optimal transport, also known as Sinkhorn divergence, has recently gained popularity in machine learning and statistics, as it makes feasible the use of smoothed optimal transportation distances for data…

Statistics Theory · Mathematics 2019-11-05 Jérémie Bigot , Elsa Cazelles , Nicolas Papadakis

Correctly estimating the discrepancy between two data distributions has always been an important task in Machine Learning. Recently, Cuturi proposed the Sinkhorn distance which makes use of an approximate Optimal Transport cost between two…

Computer Vision and Pattern Recognition · Computer Science 2018-01-18 Ying Lu , Liming Chen , Alexandre Saidi , Xianfeng Gu

We study stability and sample complexity properties of divergence regularized optimal transport (DOT). First, we obtain quantitative stability results for optimizers of DOT measured in Wasserstein distance, which are applicable to a wide…

Optimization and Control · Mathematics 2024-01-17 Erhan Bayraktar , Stephan Eckstein , Xin Zhang

Variational problems that involve Wasserstein distances and more generally optimal transport (OT) theory are playing an increasingly important role in data sciences. Such problems can be used to form an examplar measure out of various…

Machine Learning · Computer Science 2018-11-15 Marco Cuturi , Gabriel Peyré

We provide an implementation to compute the flat metric in any dimension. The flat metric, also called dual bounded Lipschitz distance, generalizes the well-known Wasserstein distance $W_1$ to the case that the distributions are of unequal…

Machine Learning · Computer Science 2025-06-17 Henri Schmidt , Christian Düll

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 novel optimal transport framework for probabilistic circuits (PCs). While it has been shown recently that divergences between distributions represented as certain classes of PCs can be computed tractably, to the best of our…

Artificial Intelligence · Computer Science 2025-10-16 Adrian Ciotinga , YooJung Choi

The Earth Mover's Distance (EMD) is a state-of-the art metric for comparing discrete probability distributions, but its high distinguishability comes at a high cost in computational complexity. Even though linear-complexity approximation…

Machine Learning · Computer Science 2019-05-29 Kubilay Atasu , Thomas Mittelholzer

We introduce the problem of transporting vector-valued distributions. In this, a salient feature is that mass may flow between vectorial entries as well as across space (discrete or continuous). The theory relies on a first step taken to…

Optimization and Control · Mathematics 2017-05-19 Yongxin Chen , Tryphon T. Georgiou , Allen Tannenbaum

Measuring similarities between different tasks is critical in a broad spectrum of machine learning problems, including transfer, multi-task, continual, and meta-learning. Most current approaches to measuring task similarities are…

Machine Learning · Computer Science 2022-08-26 Xinran Liu , Yikun Bai , Yuzhe Lu , Andrea Soltoggio , Soheil Kolouri

The challenge of describing model drift is an open question in unsupervised learning. It can be difficult to evaluate at what point an unsupervised model has deviated beyond what would be expected from a different sample from the same…

Computational Geometry · Computer Science 2018-12-18 Michael McCabe

This paper focuses on the Monge-Kantorovich formulation of the optimal transport problem and the associated $L^2$ Wasserstein distance. We use the $L^2$ Wasserstein distance in the Nearest Neighbour (NN) machine learning architecture to…

Computer Vision and Pattern Recognition · Computer Science 2019-03-20 Michael Snow , Jan Van lent

Despite the recent popularity of neural network-based solvers for optimal transport (OT), there is no standard quantitative way to evaluate their performance. In this paper, we address this issue for quadratic-cost transport --…

Machine Learning · Computer Science 2021-10-26 Alexander Korotin , Lingxiao Li , Aude Genevay , Justin Solomon , Alexander Filippov , Evgeny Burnaev

We study the problem of minimizing the Wasserstein distance between a probability distribution and an algebraic variety. We consider the setting of finite state spaces and describe the solution depending on the choice of the ground metric…

Optimization and Control · Mathematics 2020-01-15 T. Ö. Çelik , A. Jamneshan , G. Montúfar , B. Sturmfels , L. Venturello

Common measures of neural representational (dis)similarity are designed to be insensitive to rotations and reflections of the neural activation space. Motivated by the premise that the tuning of individual units may be important, there has…

Machine Learning · Computer Science 2023-11-17 Meenakshi Khosla , Alex H. Williams

Defining meaningful distances between samples in a dataset is a fundamental problem in machine learning. Optimal Transport (OT) lifts a distance between features (the "ground metric") to a geometrically meaningful distance between samples.…

Machine Learning · Statistics 2022-07-20 Geert-Jan Huizing , Laura Cantini , Gabriel Peyré

Optimal Transport (OT) metrics allow for defining discrepancies between two probability measures. Wasserstein distance is for longer the celebrated OT-distance frequently-used in the literature, which seeks probability distributions to be…

Machine Learning · Computer Science 2021-10-14 Mokhtar Z. Alaya , Gilles Gasso , Maxime Berar , Alain Rakotomamonjy