Robustness of Diffusion Models under Distribution Shift
math.ST, cs.LG, math.PR, stat.ML, stat.TH
Submitted: 2026-09-23
Updated: 2026-09-23
Comments: 13 pages, 2 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions
- Convergence of Deterministic and Stochastic Diffusion-Model Samplers: A Simple Analysis in Wasserstein Distance
- Generative Modeling with Denoising Auto-Encoders and Langevin Sampling
- Minimax Optimality of the Probability Flow ODE for Diffusion Models
- Learning general Gaussian mixtures with efficient score matching
- Generative models for decision-making under distributional shift
- Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
- DDPM Score Matching and Distribution Learning
- Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian probability distributions
- From optimal score matching to optimal sampling
- Optimal estimation of a factorizable density using diffusion models with ReLU neural networks
- Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory
- Learning Mixtures of Gaussians Using Diffusion Models
- Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization
- Guided Transfer Learning for Discrete Diffusion Models
- A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion Models
- Generalization bounds for score-based generative models: a synthetic proof
- Generalization error bound for denoising score matching under relaxed manifold assumption
- Implicit score matching meets denoising score matching: improved rates of convergence and log-density Hessian estimation
- Diffusion Models with Heavy-Tailed Targets: Score Estimation and Sampling Guarantees
Related papers
- Conformal Prediction for Dyadic Regression Under Complex Missingness
- Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF Kernel
- Bentkus-type asymptotic e-values
- High-Dimensional Asymptotics of Differentially Private PCA
- A proximal gradient algorithm for composite log-concave sampling
- KL Convergence Guarantees for Score diffusion models under minimal data assumptions