AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Sinkhorn Barycenter via Functional Gradient Descent

Zebang Shen, Zhenfu Wang, Alejandro Ribeiro, Hamed Hassani

NeurIPS 2020 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 6 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 Sinkhorn Descent instead of functional Frank-WolfeSinkhorn barycenter of concentric ellipses · Concentric ellipsesconvergence rateImproved
Use Sinkhorn Descent with support size 20 instead of functional Frank-Wolfe with support size 600Sinkhorn barycenter of concentric ellipses · Concentric ellipsessolution qualityImproved
Use Sinkhorn Descent instead of functional Frank-WolfeDistribution sketching · Cheetah imagesolution qualityImproved
Use Sinkhorn Descent instead of functional Frank-WolfeDistribution sketching · Cheetah imageconvergence rateImproved
Use Sinkhorn Descent for the high-dimensional barycenter problemBarycenter of Gaussians · 5 isotropic Gaussians in R^100convergence iterations: less than 20 iterationsImproved
Use Sinkhorn Descent instead of functional Frank-WolfeVisual barycenter and sketching results · Ellipses and cheetah sketchingvisual qualityImproved

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