Research map / Learning theory and algorithms / Sample complexity
Tight Bounds for Schrodinger Potential Estimation in Unpaired Data Translation
Nikita Puchkin, Denis Suchkov, Alexey Naumov, Denis Belomestny
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 |
|---|---|---|---|
| replace Wiener reference process with Ornstein-Uhlenbeck reference | LightSB · Gaussian mixture, standard | Sliced W1: 0.260 -> 0.156 | Improved |
| replace Wiener reference with OU | LightSB · Gaussian mixture, irregular | Sliced W1: 0.525 -> 0.214 | Improved |
| replace Wiener reference with OU | LightSB · Gaussian mixture, anisotropic | Sliced W1: 0.255 -> 0.206 | Improved |
| replace Wiener reference with OU | LightSB · Gaussian mixture, irregular | Mode Coverage: 21.8 -> 25.0 | Improved |
| replace Wiener reference with OU | LightSB · Gaussian mixture, standard | MMD: 0.0004 -> 0.0003 | No clear effect |
| replace Wiener reference with OU | LightSB · Single-cell intermediate distribution | W1: 0.823 -> 0.812 | No clear effect |
| replace Wiener reference with OU | LightSB · ALAE FFHQ Adult-to-Child | qualitative | Improved |
Closest papers by meaning
- Exponential Convergence Guarantees for Iterative Markovian Fitting (NeurIPS 2025 · similarity 0.87)
- Schrödinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentres (NeurIPS 2025 · similarity 0.87)
- Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-free (NeurIPS 2025 · similarity 0.87)
- Adjoint Schrödinger Bridge Sampler (NeurIPS 2025 · similarity 0.87)
- Schrodinger Bridge Flow for Unpaired Data Translation (NeurIPS 2024 · similarity 0.86)
- Go With the Flow: Fast Diffusion for Gaussian Mixture Models (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.
