Introduction to the Wasserstein distance
Title: Introduction to the Wasserstein distance Abstract: I give an introduction to the Wasserstein distance, which is also called the Kantorovich-Rubinstein, optimal transport, or earth mover's distance. In particular, I describe how the 1-Wasserstein distance is defined between probability measures with finite support, and then briefly generalize to measures with arbitrary support. I mention how geodesics with the Wasserstein metric can have much nicer than geodesics with other metrics. Notes: https://www.math.colostate.edu/~adams...
▶︎
An introduction to the Gromov-Hausdorff distance
▶︎
The Wasserstein Metric a.k.a Earth Mover's Distance: A Quick and Convenient Introduction
▶︎
Soheil Kolouri - Wasserstein Embeddings in the Deep Learning Era
▶︎
The Key Equation Behind Probability
▶︎
New Frontiers in Mathematics: Professor Cédric Villani, “Optimal Transport Theory”
▶︎
Wasserstein Distance & Optimal Transport — Fully Explained
▶︎
Rémi Flamary - Optimal Transport in Python: A Practical Introduction with POT
▶︎
The Most Elegant Way to Compare Probability Distributions
▶︎
Marco Cuturi - A Primer on Optimal Transport Part 1
▶︎
Intuitively Understanding the KL Divergence
▶︎
Earth Mover's Distance and Maximum Mean Discrepancy | Unsupervised Learning for Big Data
▶︎
An introduction to persistent homology
▶︎
Shape Analysis (Lecture 19): Optimal transport
▶︎
A brief introduction to the regularity theory of optimal transport
▶︎
Deep Learning 35: (2) Wasserstein Generative Adversarial Network (WGAN): Wasserstein metric
▶︎
23: Mahalanobis distance
▶︎
Jonathan Niles-Weed (NYU/IAS) - Estimation of the Wasserstein distance in the spiked transport model
▶︎
Marco Part A Primer on Optimal Transport Part 3
▶︎
Wasserstein GAN Part-1(KL-Divergence Vs Jensen-Shannon Divergence Vs Wasserstein Distance)
▶︎