DDPM Score Matching and Distribution Learning
stat.ML, cs.DS, cs.LG, math.ST, stat.TH
Submitted: 2025-04-07
Updated: 2026-09-04
Comments: Presented at COLT 2026; abstract shortened to fit arXiv limit
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Dimension Reduction via Sum-of-Squares and Improved Clustering Algorithms for Non-Spherical Mixtures
- Shifted Composition II: Shift Harnack Inequalities and Curvature Upper Bounds
- Outlier-Robust Clustering of Non-Spherical Mixtures
- Generative Modeling with Denoising Auto-Encoders and Langevin Sampling
- Learning general Gaussian mixtures with efficient score matching
- Robustly Learning any Clusterable Mixture of Gaussians
- From optimal score matching to optimal sampling
- Learning Mixtures of Gaussians Using Diffusion Models
- Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond
- Efficiently learning and sampling multimodal distributions with data-based initialization
- A Score-Based Density Formula, with Applications in Diffusion Generative Models
- O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal Assumptions
- Nonparametric MLE for Gaussian Location Mixtures: Certified Computation and Generic Behavior
- Generalization error bound for denoising score matching under relaxed manifold assumption
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Efficient quadratic entropy with distance sketches
- Embedding-Bias in Conditional Independence Testing
- From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier