AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Streaming Sliced Optimal Transport

Khai Nguyen

ICML 2026 · Learning theory and algorithms › Optimal transport · approach: Sliced Wasserstein variants · 0 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
replace random sampling with quantile-sketch Stream-SWSW estimation · Gaussians approximation error (n=10000, k=2)relative error: 0.289892 -> 0.0989126Improved
replace random sampling with quantile-sketch Stream-SW at large sketch sizeSW estimation · Gaussians approximation error (n=10000, k=1000)relative error: 0.0420441 -> 0.0404598No clear effect
replace random sampling with Stream-SWSW kNN classifier · ModelNet10 KNN (L=5, k=5)accuracy (%): 39.33 -> 45.53Improved
replace random sampling with Stream-SWSW kNN classifier · ModelNet10 KNN (L=100, k=10)accuracy (%): 62 -> 76.67Improved
replace random sampling with Stream-SW at large sketchSW kNN classifier · ModelNet10 KNN (L=5, k=50)accuracy (%): 61.33 -> 68.67Improved
replace random sampling with Stream-SWSW gradient flow · ShapeNet gradient flow (L=1000, k=200, step 5000)Wasserstein-2 x10^3: 6.59 -> 0.48Improved
replace random sampling with Stream-SWSW gradient flow · ShapeNet gradient flow (L=100, k=100, step 5000)Wasserstein-2 x10^3: 9.36 -> 1.93Improved
use Stream-SW instead of Full SW (all samples)SW gradient flow · ShapeNet gradient flow (L=100, step 5000)Wasserstein-2 x10^3: 0.84 -> 1.36Hurt
replace sliding-window SW with Stream-SWchange point detection · MSRC-12 Guest 2detection delay: 100 -> 10Improved
replace sliding-window SW with Stream-SWchange point detection · MSRC-12 Guest 3detection delay: 49 -> 24Improved
increase sketch size kStream-SW · ShapeNet gradient flow (L=1000, step 5000)Wasserstein-2 x10^3: 0.85 -> 0.48Improved

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