Research map / Image generation / Fast diffusion sampling
Geometric Neural Diffusion Processes
Emile Mathieu, Vincent Dutordoir, Michael John Hutchinson, Valentin De Bortoli, Yee Whye Teh, Richard E Turner
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 |
|---|---|---|---|
| Enforce translation invariance in the score network | GeomNDP · 1D stationary scalar fields, generalisation | test log-likelihood | Improved |
| Model outputs on the sphere rather than in Euclidean coordinates | GeomNDP · Cyclone extrapolation | MSE (km): 769± 48 -> 496± 14 | Improved |
| Use non-white limiting kernels instead of white noise (ablation) | GeomNDP · 1D synthetic regression datasets | test log-likelihood | Hurt |
| Use the preconditioned score K∇ log p_t parameterisation (ablation) | GeomNDP · 1D synthetic regression datasets | test log-likelihood | Improved |
| Perform multiple Langevin dynamics steps during conditional sampling (ablation) | GeomNDP conditional sampler · SE conditional sampling | KL divergence | Improved |
| Change the noising scheme for context values (ablation) | GeomNDP conditional sampler · SE conditional sampling | KL divergence | No clear effect |
Closest papers by meaning
- On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion models (ICLR 2024 · similarity 0.88)
- Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold (NeurIPS 2026 · similarity 0.88)
- Generalization through variance: how noise shapes inductive biases in diffusion models (ICLR 2025 · similarity 0.87)
- Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models (ICLR 2024 · similarity 0.87)
- Generalization in diffusion models arises from geometry-adaptive harmonic representations (ICLR 2024 · similarity 0.87)
- Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusion (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.
