Stochastic Methods for Optimal Transport in Machine Learning Applications

Thursday, November 12, 2020 - 10:40am - 11:25am
Aude Genevay (Massachusetts Institute of Technology)
We will see how optimal transport can be seen as a stochastic optimization problem, which allows to leverage stochastic gradient methods to solve related problems. Aside from an efficient online estimation of optimal transport distances, these methods can also be extended to compute Wasserstein barycenters without relying on discretization of the output.