event

Effect of Dependence on the Convergence of Empirical Wasserstein Distance

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 …

OT techniques in data driven methodology: theory and practice from mathematical finance and statistics

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 …

KI retreat 2022

The Kantorovich Initiative Retreat will take place on Friday March 18th, in Paccar Hall, room 291.

Wasserstein gradient flows for machine learning

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 …

Optimal transport theory in incomplete econometric models

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 …

A survey on weak optimal transport

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 …

Estimating transport distances via Stein's method

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 …

Conditional Sampling with Block-Triangular Transport Maps

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, …

Finite sample rates for optimal transport estimation problems

The theory of optimal transport (OT) gives rise to distance measures between probability distributions that take the geometry of the underlying space into account. OT is often used in the analysis of point cloud data, for example in domain adaptation …

Entropic Regularization of Optimal Transport and Applications (Online)

The Banff International Research Station will host the "Entropic Regularization of Optimal Transport and Applications" workshop in Banff from June 20 to June 25, 2021.