This repository contains materials for a course on Optimal Transport for Machine Learning.
In this repository, you will find the following Jupyter notebooks:
- Optimal Transport with Linear Programming
- Entropic Regularization of Optimal Transport
- Advanced Topics on Sinkhorn Algorithm
- Semi-discrete Optimal Transport
- Unbalanced Optimal Transport
- Diffusion models and Optimal Transport
- Wasserstein gradient flow of interaction functionals
You can either download these .ipynb notebooks and run them locally, or click on
to run them directly in Google Colab (requires a Google account).
- Monge and Kantorovitch
- Entropic Regularization
- Dual and Semidiscrete
- Gradient Flow and Diffusion Models
The lecture notes Optimal Transport for Machine Learners can be found at this link..
- Computational Optimal Transport, Gabriel Peyré & Marco Cuturi, 2018.
- Optimal Transport for Applied Mathematicians, Filippo Santambrogio, Springer, 2016.
- Statistical Optimal Transport, Sinho Chewi, Jonathan Niles-Weed, Philippe Rigollet, 2024.