The first part is devoted to Monge and Kantorovitch problems, discussing the existence and the properties of the optimal plan. The second part introduces the Wasserstein distance on measures and develops applications of optimal transport to PDEs, functiona ...
This course provides an overview of key advances in continuous optimization and statistical analysis for machine learning. We review recent learning formulations and models as well as their guarantees
The Loss Landscape of Neural Networks is in general non-convex and rough, but recent mathematical results lead provide insights of practical relevance.
9 online lectures, lecturers from NYU, Stanford, Shanghai, IST Austria, Google, Facebook, EPFL. ...