Concepedia

Concept

wasserstein distance

Parents

647

Publications

46.5K

Citations

1.3K

Authors

564

Institutions

About

Wasserstein distance is a class of metrics used to measure the distance between two probability distributions defined on a common metric space. Grounded in optimal transport theory, it quantifies the minimum "cost" required to transform one distribution into the other, where cost is typically defined by the distance in the underlying space. This approach provides a geometrically informed comparison between distributions, offering robustness and sensitivity to the structure of the data space, which is particularly valuable in fields like machine learning, image analysis, and topological data analysis.

Top Authors

Rankings shown are based on concept H-Index.

MC

Kyoto University

GP

Centre de Recherche en Mathématiques de la Décision

TT

University of Minnesota

JB

Institut de Mathématiques de Toulouse

AT

Georgia Institute of Technology