University of Washington

Entropic optimal transport has received a lot of attention in recent years and has become a popular framework for computational optimal transport thanks to the Sinkhorn scaling algorithm. In this talk, I will discuss the multi-marginal case which...

Generative models such as Generative Adversarial Nets (GANs), Variational Autoencoders and Normalizing Flows have been very successful in the unsupervised learning task of generating samples from a high-dimensional probability distribution. However...

Stein’s method is a set of techniques for bounding distances between probability measures via integration-by-parts formulas. It was introduced by Stein in the 1980s for bouding the rate of convergence in central limit theorems, and has found many...

This talk will present the framework of weak optimal transport which allows to incorporate more general penalizations on elementary mass transports. After recalling general duality results and different optimality criteria, we will focus on recent...

This talk focuses on the central role played by optimal transport theory in the study of incomplete econometric models. Incomplete econometric models are designed to analyze microeconomic data within the constraints of microeconomic theoretic...

An important problem in machine learning and computational statistics is to sample from an intractable target distribution, e.g. to sample or compute functionals (expectations, normalizing constants) of the target distribution. This sampling problem...

Wasserstein distances, or Optimal Transport methods more generally, offer a powerful non-parametric toolbox to conceptualise and quantify model uncertainty in diverse applications. Importantly, they work across the spectrum: from small uncertainty...

In optimal transport problems on a finite set, one successful approach to reducing its computational burden is the regularization by the Kullback-Leibler divergence. Then a natural question arises: Are other divergences not admissible for...

The Wasserstein distance is a powerful tool in modern machine learning to metrize the space of probability distributions in a way that takes into account the geometry of the domain. Therefore, a lot of attention has been devoted in the literature to...

Detecting differences and building classifiers between distributions, given only finite samples, are important tasks in a number of scientific fields. Optimal transport (OT) has evolved as the most natural concept to measure the distance between...