Recent Advances in Optimal Transport for Machine Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-02 · 47 (2) · 1161-1180
DOI: 10.1109/tpami.2024.3489030 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-02. Verfasst von Eduardo Fernandes Montesuma und 2 weiteren Autor:innen. Die Arbeit wurde bisher 58-mal zitiert (Crossref) und nennt 176 Literaturangaben.
Abstract (Originalsprache)
Recently, Optimal Transport has been proposed as a probabilistic framework in Machine Learning for comparing and manipulating probability distributions. This is rooted in its rich history and theory, and has offered new solutions to different problems in machine learning, such as generative modeling and transfer learning. In this survey we explore contributions of Optimal Transport for Machine Learning over the period 2012 - 2023, focusing on four sub-fields of Machine Learning: supervised, unsupervised, transfer and reinforcement learning. We further highlight the recent development in computational Optimal Transport and its extensions, such as partial, unbalanced, Gromov and Neural Optimal Transport, and its interplay with Machine Learning practice.
Zitieren
APA
Montesuma, E. F., Mboula, F. N., & Souloumiac, A. (2025). Recent Advances in Optimal Transport for Machine Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(2), 1161-1180. https://doi.org/10.1109/tpami.2024.3489030
Vancouver
Montesuma EF, Mboula FN, Souloumiac A. Recent Advances in Optimal Transport for Machine Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(2):1161-1180. doi:10.1109/tpami.2024.3489030
BibTeX
@article{Montesuma2025,
author = {Montesuma, Eduardo Fernandes and Mboula, Fred Ngole and Souloumiac, Antoine},
title = {Recent Advances in Optimal Transport for Machine Learning},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {2},
pages = {1161--1180},
doi = {10.1109/tpami.2024.3489030}
}
EUVIMED