AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark

NeurIPS 2023 · Learning theory and algorithms › Optimal transport · approach: Schrodinger bridge matching · 1 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 EOT solvers LSOT and SCONES at medium/large epsilonLSOT, SCONES · Mixtures pairs, epsilon 1 and 10cBW2-UVPHurt
run LSOT and SCONES at epsilon 0.1LSOT, SCONES · Mixtures pairs, epsilon 0.1BW2-UVPHurt
use conditional normalizing flow as generator in NOTNOT · Mixtures pairscBW2-UVPHelped
increase epsilon from 0.1 to 10SB solvers (ENOT, MLE-SB, DiffSB, FB-SDE) · Mixtures pairsBW2-UVPHurt
use default hyperparameters at epsilon 10DiffSB, FB-SDE-A, FB-SDE-J · Mixtures pairs, epsilon 10BW2-UVPHurt
increase epsilon from 0.1 to 10ENOT · CelebA 64x64 images pairsimage restoration precisionMixed
apply SCONES, DiffSB, FB-SDE-A, NOT to high-dimensional imagesSCONES, DiffSB, FB-SDE-A, NOT · CelebA 64x64 images pairstraining convergenceHurt
EgNOT instead of other EOT solvers for matching target marginalEgNOT · Mixtures pairsBW2-UVPHelped

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