English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Optimal transport aims to estimate a transportation plan that minimizes adisplacement cost. This is realized by optimizing the scalar product betweenthe sought plan and the given cost, over the space of doubly stochasticmatrices. When the entropy regularization is added to the problem, thetransportation plan can be efficiently computed with the Sinkhorn algorithm.Thanks to this breakthrough, optimal transport has been progressively extendedto machine learning and statistical inference by introducing additionalapplication-specific terms in the problem formulation. It is howeverchallenging to design efficient optimization algorithms for optimal transportbased extensions. To overcome this limitation, we devise a generalforward-backward splitting algorithm based on Bregman distances for solving awide range of optimization problems involving a differentiable function withLipschitz-continuous gradient and a doubly stochastic constraint. We illustratethe efficiency of our approach in the context of continuous domain adaptation.Experiments show that the proposed method leads to a significant improvement interms of speed and performance with respect to the state of the art for domainadaptation on a continually rotating distribution coming from the standard twomoon dataset.

Forward-Backward Splitting for Optimal Transport based Problems