Fast Convergence for High-Order ODE Solvers in Diffusion Probabilistic Models
cs.LG, cs.NA, math.CA, math.NA
Submitted: 2025-06-16
Updated: 2026-09-11
Comments: 69 pages, 7 figures
Code: https://github.com/lucidrains/denoising-diffusion-pytorch
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Stochastic Interpolants: A Unifying Framework for Flows and Diffusions
- Building Normalizing Flows with Stochastic Interpolants
- Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions
- Error Bounds for Flow Matching Methods
- Generative Modeling with Denoising Auto-Encoders and Langevin Sampling
- Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach
- Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
- Sampling via Gradient Flows in the Space of Probability Measures
- Statistical optimal transport
- Jukebox: A Generative Model for Music
- Convergence Analysis for General Probability Flow ODEs of Diffusion Models in Wasserstein Distances
- Denoising diffusion probabilistic models are optimally adaptive to unknown low dimensionality
- Auto-Encoding Variational Bayes
- Dimension-Free Convergence of Diffusion Models for Approximate Gaussian Mixtures
- Accelerating Convergence of Score-Based Diffusion Models, Provably
- Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models
- A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion Models
- Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
- O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal Assumptions
- Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks