Recent Advances in Optimal Transport for Machine Learning
It provides a comprehensive overview for researchers, but is incremental as it synthesizes existing work without introducing novel findings.
This survey explores the application of Optimal Transport as a probabilistic framework in machine learning from 2012 to 2023, covering areas like generative modeling and transfer learning, but does not present new results or concrete numbers.
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.