Recent Advances in Optimal Transport for Machine Learning
TL
TL;DR
This survey explores 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.
Abstract
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.
References203 items
1
Federated Wasserstein Distance
2
Federated Dataset Dictionary Learning for Multi-Source Domain Adaptation
3
Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Space
4
Spherical Sliced-Wasserstein
5