Research map / Probabilistic and scientific modeling / Dynamical systems
Deep Momentum Multi-Marginal Schrödinger Bridge
Tianrong Chen, Guan-Horng Liu, Molei Tao, Evangelos Theodorou
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use DMSB instead of the strongest baseline | scRNA-seq trajectory inference · scRNA-seq 100-D w/o LO | MMD: 0.23 -> 0.03 | Improved |
| Use DMSB instead of the strongest baseline | scRNA-seq trajectory inference · scRNA-seq 100-D LO-t1 | MMD: 0.23 -> 0.04 | Improved |
| Use DMSB instead of the strongest baseline | scRNA-seq trajectory inference · scRNA-seq 100-D LO-t2 | MMD: 0.37 -> 0.04 | Improved |
| Use DMSB instead of the strongest baseline | scRNA-seq trajectory inference · scRNA-seq 100-D LO-t3 | MMD: 0.23 -> 0.04 | Improved |
| Use DMSB instead of the strongest baseline | scRNA-seq trajectory inference · scRNA-seq 100-D w/o LO | SWD: 0.35 -> 0.20 | Improved |
| Use DMSB instead of the strongest baseline | scRNA-seq trajectory inference · scRNA-seq 100-D LO-t1 | SWD: 0.49 -> 0.20 | Improved |
| Use DMSB instead of the strongest baseline | scRNA-seq trajectory inference · scRNA-seq 100-D LO-t2 | SWD: 0.54 -> 0.19 | Improved |
| Use DMSB instead of the strongest baseline | scRNA-seq trajectory inference · scRNA-seq 100-D LO-t3 | SWD: 0.50 -> 0.18 | Improved |
| Infer dynamics with DMSB from position snapshots without velocity labels | 100-D scRNA-seq · scRNA-seq 100-D | velocity distribution discrepancy | Improved |
Closest papers by meaning
- Momentum Multi-Marginal Schrödinger Bridge Matching (NeurIPS 2025 · similarity 0.93)
- Trajectory Inference with Smooth Schrödinger Bridges (ICML 2025 · similarity 0.90)
- Go With the Flow: Fast Diffusion for Gaussian Mixture Models (NeurIPS 2025 · similarity 0.89)
- Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-free (NeurIPS 2025 · similarity 0.88)
- Adjoint Schrödinger Bridge Sampler (NeurIPS 2025 · similarity 0.87)
- Generalized Schrödinger Bridge Matching (ICLR 2024 · similarity 0.87)
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.
