Hilbert's projective metric for functions of bounded growth and exponential convergence of Sinkhorn's algorithm

S Eckstein - arXiv preprint arXiv:2311.04041, 2023 - arxiv.org
We study versions of Hilbert's projective metric for spaces of integrable functions of bounded
growth. These metrics originate from cones which are relaxations of the cone of all non …

An ordinary differential equation for entropic optimal transport and its linearly constrained variants

JZG Hiew, L Nenna, B Pass - arXiv preprint arXiv:2403.20238, 2024 - arxiv.org
We characterize the solution to the entropically regularized optimal transport problem by a
well-posed ordinary differential equation (ODE). Our approach works for discrete marginals …

A regularized transportation cost stemming from entropic approximation

C Brizzi, L De Pascale, A Kausamo - arXiv preprint arXiv:2501.03906, 2025 - arxiv.org
We study the entropic regularizations of optimal transport problems under suitable
summability assumptions on the point-wise transport cost. These summability assumptions …

On some generalisations of Optimal Transport problem

L Nenna - 2024 - inria.hal.science
This manuscript is devoted to the study of some generalisation of Optimal Transport problem
as well as some applications arising in Mathematical Finance, Game Theory and Quantum …

Neural Entropic Multimarginal Optimal Transport

D Tsur, Z Goldfeld, K Greenewald… - OPT 2024: Optimization … - openreview.net
Multimarginal optimal transport (MOT) is a powerful framework for modeling interactions
between multiple distributions, yet its applicability is bottlenecked by a high computational …

[PDF][PDF] M2 subject” ODE characterisation of entropic optimal transport”

L Nenna, P Pegon - 2023 - lucanenna.github.io
A natural way to solve numerically the optimal transport problem is by means of the well
known entropic regularization: that is, given 2 probability measures µ1 and µ2 and a cost …