# Adversarial Optimal Transport Through The Convolution Of Kernels With Evolving Measures

7 Jun 2020Daeyoung KimEsteban G. Tabak

A novel algorithm is proposed to solve the sample-based optimal transport problem. An adversarial formulation of the push-forward condition uses a test function built as a convolution between an adaptive kernel and an evolving probability distribution $\nu$ over a latent variable $b$... (read more)

PDF Abstract