Computational optimal transport: With applications to data science

G Peyré, M Cuturi - Foundations and Trends® in Machine …, 2019 - nowpublishers.com
Optimal transport (OT) theory can be informally described using the words of the French
mathematician Gaspard Monge (1746–1818): A worker with a shovel in hand has to move a …

Wasserstein distributionally robust optimization: Theory and applications in machine learning

D Kuhn, PM Esfahani, VA Nguyen… - … science in the age …, 2019 - pubsonline.informs.org
Many decision problems in science, engineering, and economics are affected by uncertain
parameters whose distribution is only indirectly observable through samples. The goal of …

Smooth and sparse optimal transport

M Blondel, V Seguy, A Rolet - International conference on …, 2018 - proceedings.mlr.press
Entropic regularization is quickly emerging as a new standard in optimal transport (OT). It
enables to cast the OT computation as a differentiable and unconstrained convex …

When optimal transport meets information geometry

G Khan, J Zhang - Information Geometry, 2022 - Springer
Abstract Information geometry and optimal transport are two distinct geometric frameworks
for modeling families of probability measures. During the recent years, there has been a …

Sinkhorn autoencoders

G Patrini, R Van den Berg, P Forre… - Uncertainty in …, 2020 - proceedings.mlr.press
Optimal transport offers an alternative to maximum likelihood for learning generative
autoencoding models. We show that minimizing the $ p $-Wasserstein distance between the …

Polynomial-time algorithms for multimarginal optimal transport problems with structure

JM Altschuler, E Boix-Adsera - Mathematical Programming, 2023 - Springer
Abstract Multimarginal Optimal Transport (MOT) has attracted significant interest due to
applications in machine learning, statistics, and the sciences. However, in most applications …

Regularized optimal transport and the rot mover's distance

A Dessein, N Papadakis, JL Rouas - Journal of Machine Learning …, 2018 - jmlr.org
This paper presents a unified framework for smooth convex regularization of discrete optimal
transport problems. In this context, the regularized optimal transport turns out to be …

[PDF][PDF] Scalable computation of monge maps with general costs

J Fan, S Liu, S Ma, Y Chen, H Zhou - arXiv preprint arXiv …, 2021 - researchgate.net
Monge map refers to the optimal transport map between two probability distributions and
provides a principled approach to transform one distribution to another. In spite of the rapid …

Information geometry connecting Wasserstein distance and Kullback–Leibler divergence via the entropy-relaxed transportation problem

S Amari, R Karakida, M Oizumi - Information Geometry, 2018 - Springer
Two geometrical structures have been extensively studied for a manifold of probability
distributions. One is based on the Fisher information metric, which is invariant under …

Learning to match via inverse optimal transport

R Li, X Ye, H Zhou, H Zha - Journal of machine learning research, 2019 - jmlr.org
We propose a unified data-driven framework based on inverse optimal transport that can
learn adaptive, nonlinear interaction cost function from noisy and incomplete empirical …