Non-asymptotic Convergence of Stochastic Gradient Descent in Score-based Generative Models

arXiv:2607.04775 · stat.ML, cs.LG · Submitted 2026-07-06 · Read on arXiv

SU, LPSM · SU, LPSM · SU, LPSM

stat.ML, cs.LG

Submitted: 2026-07-06

Updated: 2026-10-07

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Diffusion Model — 24× in this paper · explained in 10 episodes
• Diffusion Models — 24× in this paper · explained in 9 episodes
• Generative Model — 17× in this paper · explained in 2 episodes
• Generative Models — 15× in this paper · explained in 3 episodes
• Parameterization — 11× in this paper · explained in 2 episodes
• Generalization — 9× in this paper · explained in 14 episodes
• ReLU Network — 9× in this paper · explained in 2 episodes
• Neural Tangent Kernel — 6× in this paper
• Score Function — 6× in this paper · explained in 4 episodes
• Stochastic Gradient Descent — 6× in this paper
• Convergence Guarantees — 5× in this paper · explained in 3 episodes
• Generative Modeling — 5× in this paper · explained in 3 episodes
• Localization — 5× in this paper · explained in 2 episodes
• Generalization Bounds — 3× in this paper · explained in 2 episodes
• Error Decomposition — 2× in this paper · explained in 4 episodes
• Stochastic Gradient Descent (SGD) — 2× in this paper · explained in 5 episodes
• VC Dimension — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Curse of Dimensionality — 1× in this paper · explained in 6 episodes
• Denoising Autoencoder — 1× in this paper · explained in 2 episodes
• Editor — 1× in this paper · explained in 2 episodes
• Latent Diffusion Model — 1× in this paper · explained in 3 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Neural Tangent Kernel (NTK) — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Training Objective — 1× in this paper · explained in 3 episodes
• U-Net Architecture — 1× in this paper · explained in 5 episodes
• Unsupervised Learning — 1× in this paper · explained in 2 episodes

Sources

• Generalization bounds for score-based generative models: a synthetic proof
• On Forgetting and Stability of Score-based Generative models

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
• Scalable Posterior Uncertainty for Flexible Density-Based Clustering
• A Transport Geometry of Benign Overfitting
• Efficient quadratic entropy with distance sketches