AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Sliced Wasserstein Regression

Han Chen, Yidong Zhou, Hans-Georg Müller

JMLR 2026 · Learning theory and algorithms › Optimal transport · approach: Sliced Wasserstein variants

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 SWW (slice-wise) instead of SAW (slice-averaged)SAW · global regression, Gaussian p=2 n=200ISE: 0.073 -> 0.037Improved
use SWW instead of SAWSAW · local regression, Gaussian p=2 n=50ISE: 0.150 vs 0.126Hurt
use SWW instead of SAWSAW · global regression, non-Gaussian p=5 n=200ISE: 0.071 -> 0.019Improved
use sliced regression (SWW) instead of FM (Sinkhorn)FM · global Gaussian p=2 n=200ISE: 0.416 -> 0.037Improved
use sliced regression (SAW) instead of FMFM · local non-Gaussian p=2 n=200ISE: 0.422 -> 0.073Improved
increase sample size n from 50 to 200 (ablation)SWW · global Gaussian p=2ISE: 0.080 -> 0.037Improved
increase sample size n from 50 to 200 (ablation)FM · global Gaussian p=2ISE: 0.460 -> 0.416Improved
use SWW instead of FM for runtimeFM · global p=2 n=200runtime (s): 285.62 -> 1.42Improved
use SWW instead of SAW for runtimeSAW · global p=5 n=200runtime (s): 130.45 -> 4.83Improved
make responses non-Gaussian via random transport mapSWW · global p=5 n=200ISE: 0.027 -> 0.019No clear effect

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