19 citations · 52 across the 6 of their papers we have counts for
8 papers
Optimal Transport losses and Sinkhorn algorithm with general convex regularization
Simone Di Marino, Augusto Gerolin
We introduce a new class of convex-regularized Optimal Transport losses, which generalizes the classical Entropy-regularization of Optimal Transport and Sinkhorn divergences, and p…
Learning normalizing flows from Entropy-Kantorovich potentials
Chris Finlay, Augusto Gerolin, Adam M Oberman +1
We approach the problem of learning continuous normalizing flows from a dual perspective motivated by entropy-regularized optimal transport, in which continuous normalizing flows a…
Entropy-Regularized -Wasserstein Distance between Gaussian Measures
Anton Mallasto, Augusto Gerolin, Hà Quang Minh
Gaussian distributions are plentiful in applications dealing in uncertainty quantification and diffusivity. They furthermore stand as important special cases for frameworks providi…
Kinetic correlation functionals from the entropic regularisation of the strictly-correlated electrons problem
Augusto Gerolin, Juri Grossi, Paola Gori-Giorgi
We investigate whether the entropic regularisation of the strictly-correlated-electrons problem can be used to build approximations for the kinetic correlation energy functional at…
An Optimal Transport approach for the Schrödinger bridge problem and convergence of Sinkhorn algorithm
Simone Di Marino, Augusto Gerolin
This paper exploit the equivalence between the Schrödinger Bridge problem and the entropy penalized optimal transport in order to find a different approach to the duality, in the s…
How Well Do WGANs Estimate the Wasserstein Metric?
Anton Mallasto, Guido Montúfar, Augusto Gerolin
Generative modelling is often cast as minimizing a similarity measure between a data distribution and a model distribution. Recently, a popular choice for the similarity measure ha…