Research map / Probabilistic and scientific modeling / Variational and generative sampling
Flow Matching for Scalable Simulation-Based Inference
Jonas Bernhard Wildberger, Maximilian Dax, Simon Buchholz, Stephen R Green, Jakob H. Macke, Bernhard Schölkopf
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 FMPE instead of NPE | posterior estimation · GW150914 | mean JSD (mnat): 3.6~\text{mnat} -> 0.5~\text{mnat} | Improved |
| Use FMPE instead of NPE | posterior estimation · GW150914 | training time: \approx 3~\text{days} -> \approx 2~\text{days} | Improved |
| Use FMPE with an optimal transport path instead of the tested score-based model | SBI benchmark tasks · SBI benchmark | performance | Improved |
| Use a power-law time prior with α > 0 instead of a uniform time prior (ablation) | FMPE · tasks with sharp bounds, including Two Moons | learning performance | Improved |
| Use gated linear units for (t, θ) conditioning on high-dimensional-observation benchmark tasks (ablation) | FMPE · B-GLM-Raw and SLCP-D | performance | Improved |
Closest papers by meaning
- FNOPE: Simulation-based inference on function spaces with Fourier Neural Operators (NeurIPS 2025 · similarity 0.87)
- Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment (CVPR 2025 · similarity 0.87)
- Consistency Models for Scalable and Fast Simulation-Based Inference (NeurIPS 2024 · similarity 0.87)
- Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows (NeurIPS 2024 · similarity 0.87)
- Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling (ICLR 2025 · similarity 0.86)
- Discrete Flow Matching (NeurIPS 2024 · 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.
