Research map / Probabilistic and scientific modeling / Variational and generative sampling
Contact Wasserstein Geodesics for Non-Conservative Schrödinger Bridges
Andrea Testa, Søren Hauberg, Tamim Asfour, Leonel Rozo
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 CWG instead of GSBM | bridge solver · LiDAR Navigation | Optimality: 2.18 -> 1.40 | Improved |
| use CWG instead of DSBM | bridge solver · LiDAR Navigation | Optimality: 4.16 -> 1.40 | Improved |
| use CWG instead of GSBM | bridge solver · LiDAR Navigation | Feasibility: 0.83 -> 0.06 | Improved |
| use CWG instead of GSBM | bridge solver · LiDAR Navigation | training time (s): 1570 -> 280 | Improved |
| use CWG instead of DM-SB | mmSB solver · Single Cell Sequencing (EB) | W2 error at t1: 2.25 -> 1.11 | Improved |
| use CWG instead of SBIRR | mmSB solver · Single Cell Sequencing (EB) | W2 error at t3: 1.86 -> 0.33 | Improved |
| use CWG instead of DM-SB | mmSB solver · Single Cell Sequencing (EB) | training time (s): 38120 -> 710 | Improved |
| use CWG instead of DSBM | bridge solver · FFHQ adult-to-child transfer | Optimality: 198.0 -> 218.1 | Hurt |
| use CWG instead of GSBM | bridge solver · FFHQ adult-to-child transfer | Feasibility: 6.839 -> 4.332 | Improved |
| use CWG instead of GSBM | bridge solver · FFHQ adult-to-child transfer | training time (s): 2650 -> 930 | Improved |
| use CWG instead of SB-Flow | bridge solver · FFHQ adult-to-child transfer | Feasibility: 21.748 -> 4.332 | Improved |
Closest papers by meaning
- Generalized Schrödinger Bridge Matching (ICLR 2024 · similarity 0.88)
- Light and Optimal Schrödinger Bridge Matching (ICML 2024 · similarity 0.87)
- Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-free (NeurIPS 2025 · similarity 0.87)
- Schrödinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentres (NeurIPS 2025 · similarity 0.87)
- Feedback Schrödinger Bridge Matching (ICLR 2025 · similarity 0.87)
- Momentum Multi-Marginal Schrödinger Bridge Matching (NeurIPS 2025 · similarity 0.86)
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.
