Title: A Review of Optimal Transport in Modern Machine Learning

Abstract: The last decade is a witness to the remarkable contributions of OT  to machine learning. In this talk, we ask where and how optimal transport is used in machine learning with a focus on the question of scalability. We will that see OT was leveraged in many modern ML problems from object detection and multimodal learning to domain adaptation and generative modeling. We also discuss methods that tried to scale optimal transport to cope with the current demands of big and high dimensional data.