In summer of 2022, we will be hosting a summer school in Optimal Transport at
the University of Washington
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, …
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 …
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.
The CMS is organizing three-hour mini-courses to be held Friday June 4th. One
of these courses will be on "Optimal Transport and Stochastic Processes on
Developmental Biology". This course may be of interest to the KI community.
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 …
The theory of large deviations provides with a way to compute asymptotically the probability that an interacting particle system moves from a given configuration to another one over a fixed time interval. The problem of finding the most likely …
The optimal transport problem provides a fundamental and quantitative way to
measure the distance between probability distributions. Recently, it has been
successfully used to analyze the evolutionary dynamics in physics and biology.
Motivated by …
The kickoff event for PIHOT (the Pacific Interdisciplinary hub on Optimal
Transport) will take place on Jan 29-30th, 2021. Please see below for a
tentative schedule and connection instructions.
Consider the problem of finding the optimal coupling (or matching) between two
i.i.d. samples from respective two densities on Euclidean spaces. For both
computational efficiency and smoothness, this discrete problem is usually
regularized by an …