AI Chat AI Image Generator AI Video Text to Speech

Implementation of batched Sinkhorn iterations for entropy-regularized Wasserstein loss

07/01/2019

∙

by Thomas Viehmann, et al.

∙

∙

In this report, we review the calculation of entropy-regularised Wasserstein loss introduced by Cuturi and document a practical implementation in PyTorch.

page 1

page 2

page 3

page 4

research

∙ 07/25/2023

Computational Guarantees for Doubly Entropic Wasserstein Barycenters via Damped Sinkhorn Iterations

We study the computation of doubly regularized Wasserstein barycenters, ...

0 Lenaïc Chizat, et al. ∙

research

∙ 02/25/2022

The concavity of generalized entropy powers

In this note we introduce a new family of entropy powers which are relat...

0 Mario Bukal, et al. ∙

research

∙ 01/29/2019

Variational Characterizations of Local Entropy and Heat Regularization in Deep Learning

The aim of this paper is to provide new theoretical and computational un...

0 Nicolas Garcia Trillos, et al. ∙

research

∙ 06/03/2020

Debiased Sinkhorn barycenters

Entropy regularization in optimal transport (OT) has been the driver of ...

7 Hicham Janati, et al. ∙

research

∙ 05/28/2020

Adversarial Classification via Distributional Robustness with Wasserstein Ambiguity

We study a model for adversarial classification based on distributionall...

0 Nam Ho-Nguyen, et al. ∙

research

∙ 10/13/2022

Continued fraction representations of the generalized operator entropy

The direct calculation of the Generalized operator entropy proves diffic...

0 Sarra Ahallal, et al. ∙

research

∙ 07/14/2020

Accelerating the identification of informative reduced representations of proteins with deep learning for graphs

The limits of molecular dynamics (MD) simulations of macromolecules are ...

0 Federico Errica, et al. ∙