Research map / Image generation / Fast diffusion sampling
Drift Estimation for Diffusion Processes Using Neural Networks Based on Discretely Observed Independent Paths
Yuzhen Zhao, Yating Liu, Marc Hoffmann
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 neural network estimator instead of B-spline estimator | drift estimator · Synthetic diffusion drift, d=1 and d=2 | convergence rate of estimation risk in N | Improved |
| use neural network estimator instead of B-spline estimator | drift estimator · Synthetic diffusion drift, N=5000, 1D and 2D | recovery of local fluctuations | Improved |
| increase dimension d with neural network estimator | NN drift estimator · Synthetic diffusion drift, d in {1,2,10,50} | empirical convergence rate vs theoretical bound: matches bound for d in {1,2,50}; slightly exceeds for d=10 | Mixed |
Closest papers by meaning
- Statistical Spatially Inhomogeneous Diffusion Inference (AAAI 2024 · similarity 0.91)
- Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling (NeurIPS 2024 · similarity 0.87)
- Neural Jump-Diffusion Temporal Point Processes (ICML 2024 · similarity 0.86)
- In-Context Learning of Stochastic Differential Equations with Foundation Inference Models (NeurIPS 2025 · similarity 0.86)
- Learning diffusion at lightspeed (NeurIPS 2024 · similarity 0.86)
- Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models (ICLR 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.
