Research map / Image generation / Fast diffusion sampling
Polynomial Convergence of Riemannian Diffusion Models
Xingyu Xu, Ziyi Zhang, Yorie Nakahira, Guannan Qu, Yuejie Chi
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 |
|---|---|---|---|
| decrease stepsize h on S^2 and T^2 | RSGM sampler · Reset probability on S^2/T^2 | log reset probability | Improved |
| increase torus dimension d in {2,4,8} | RSGM sampler · Reset probability on T^d | decay rate of reset probability | No clear effect |
| increase number of reverse steps | RSGM sampler · Warped Gaussian mixture on T^d (d=1,2,3) | TV distance | Improved |
Closest papers by meaning
- Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes (ICML 2024 · similarity 0.92)
- Efficient Diffusion Models for Symmetric Manifolds (ICML 2025 · similarity 0.91)
- Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity (NeurIPS 2025 · similarity 0.89)
- Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusion (ICLR 2025 · similarity 0.89)
- Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models (ICLR 2024 · similarity 0.89)
- Riemannian Proximal Sampler for High-accuracy Sampling on Manifolds (NeurIPS 2025 · similarity 0.88)
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.
