Research map / Probabilistic and scientific modeling / Variational and generative sampling
Stochastic Normalizing Flows
Hao Wu, Jonas Köhler, Frank Noe
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 a trainable diffusion coefficient instead of fixed identity diffusion (ablation) | Stochastic normalizing flow · Banana-shaped distribution | sampler adaptation to curvature | Improved |
| Increase the diffusion scale λ (ablation) | Stochastic normalizing flow · Ten-pointed star-shaped distribution | generative variance | Improved |
| Increase the diffusion scale λ (ablation) | Stochastic normalizing flow · Ten-pointed star-shaped distribution | smoothing of minor details | Improved |
| Set the diffusion scale λ to zero, removing stochastic noise (ablation) | Stochastic normalizing flow · Ten-pointed star-shaped distribution | stochasticity | Hurt |
| Train the diffusion coefficient for a targeted SDE | Stochastic normalizing flow · Cauchy distribution | learned diffusion profile | Improved |
Closest papers by meaning
- Scalable Equilibrium Sampling with Sequential Boltzmann Generators (ICML 2025 · similarity 0.88)
- Sequential Controlled Langevin Diffusions (ICLR 2025 · similarity 0.88)
- Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows (NeurIPS 2024 · similarity 0.88)
- NETS: A Non-equilibrium Transport Sampler (ICML 2025 · similarity 0.88)
- Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations (ICML 2024 · similarity 0.88)
- Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics (ICLR 2025 · 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.
