Information Geometry for Regularized Optimal Transport and Barycenters of Patterns

DOI10.1162/neco_a_01178zbMath1478.53020OpenAlexW2921069803WikidataQ92441372 ScholiaQ92441372MaRDI QIDQ5154148

Masafumi Oizumi, Ryo Karakida, Marco Cuturi, Shun-ichi Amari

Publication date: 1 October 2021

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/neco_a_01178

zbMATH Keywords

divergenceprobability distributionsoptimal transportationWasserstein geometryentropic regularization

Mathematics Subject Classification ID

Distribution theory (60E99) Differential geometric aspects of statistical manifolds and information geometry (53B12) Optimal transportation (49Q22) Information geometry (statistical aspects) (62B11)

Related Items

Optimal transportation plans with escort entropy regularization, Pseudo-Riemannian geometry encodes information geometry in optimal transport, Limit distributions and sensitivity analysis for empirical entropic optimal transport on countable spaces, Information Geometry, Information geometry, Clustering patterns connecting COVID-19 dynamics and human mobility using optimal transport, Wasserstein statistics in one-dimensional location scale models, Wasserstein statistics in one-dimensional location-scale models

Cites Work

• Unnamed Item
• Information geometry and its applications
• Information geometry connecting Wasserstein distance and Kullback-Leibler divergence via the entropy-relaxed transportation problem
• Convolutional wasserstein distances
• Barycenters in the Wasserstein Space
• A Smoothed Dual Approach for Variational Wasserstein Problems
• Iterative Bregman Projections for Regularized Transportation Problems
• A Relationship Between Arbitrary Positive Matrices and Doubly Stochastic Matrices