AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Unbalanced Optimal Transport through Non-negative Penalized Linear Regression

Laetitia Chapel, Rémi Flamary, Haoran Wu, Cédric Févotte, Gilles Gasso

NeurIPS 2021 · Learning theory and algorithms › Optimal transport · approach: Sinkhorn and entropic OT algorithms · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Lasso solvers (Celer, scikit-learn coordinate descent) instead of BFGS for l2-penalized UOT at large lambdal2-penalized UOT · n=m=500 Gaussian pointsrunning timeImproved
use multiplicative or Lasso/path algorithms instead of BFGS for l2-penalized UOT at any lambdal2-penalized UOT · n=m=500 Gaussian pointsrunning timeImproved
use BFGS instead of multiplicative algorithm for KL-penalized UOT at large lambdaKL-penalized UOT · n=m=500 Gaussian pointsrunning timeMixed
increase lambda (more points classified) in regularization path for domain adaptationUOT label propagation · MNIST 0-3 source to MNIST 0,1 plus Fashion-MNIST 8,9 targetoverall accuracyImproved
include outliers in the labeled set as lambda increasesUOT label propagation · MNIST/Fashion-MNIST domain adaptationcurrent accuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy