KI Seminar (online)

Modern machine learning methods, in particular deep learning approaches, have enjoyed unparalleled success in a variety of challenging …

In optimal transport problems on a finite set, one successful approach to reducing its computational burden is the regularization by …

Optimal transportation, at its core, is a powerful framework for obtaining structured yet general couplings between general probability …

Detecting differences and building classifiers between distributions, given only finite samples, are important tasks in a number of …

Wasserstein distances, or Optimal Transport methods more generally, offer a powerful non-parametric toolbox to conceptualise and …