REVIEW 7 cited by
Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more applications in science and beyond. The \textit{manifold hypothesis} states that high-dimensional data often lie on lower-dimensional manifolds within the ambient space, and is widely believed to hold in provided examples. While recent results have provided invaluable insight into how diffusion models adapt to the manifold hypothesis, they do not capture the great empirical success of these models, making this a very fruitful research direction. In this work, we study DDPMs under the manifold hypothesis and prove that they achieve rates independent of the ambient dimension in terms of score learning. In terms of sampling complexity, we obtain rates independent of the ambient dimension w.r.t. the Kullback-Leibler divergence, and $O(\sqrt{D})$ w.r.t. the Wasserstein distance. We do this by developing a new framework connecting diffusion models to the well-studied theory of extrema of Gaussian Processes.
Forward citations
Cited by 7 Pith papers
-
Exact simulation of diffusions and improved algorithms for log-concave sampling
Path-space rejection sampling with unbiased Girsanov ratio estimators yields log-concave samplers with O-tilde(kappa^{2/3} d^{1/3}) queries, improving prior kappa d^{1/2} MALA complexity.
-
Fast Score-Based Sampling via Log-Concave Reductions
Score-based sampling reduces to a short sequence of strongly log-concave sampling problems, giving √d polylog(1/ε) complexity bounds and logarithmic dependence on the condition number for log-concave targets.
-
Generalization bounds for score-based generative models: a synthetic proof
Score-based generative models achieve minimax optimal W1 rates n^{-(β+1)/(2β+d)} over β-Hölder densities, up to polylog factors.
-
Faster Diffusion Models via Higher-Order Approximation
A new higher-order ODE sampler for diffusion models is proven to reach ε total-variation accuracy with eO(d^{1+2/K}/ε^{1/K}) iterations under mild assumptions.
-
Assessing the Quality of Denoising Diffusion Models in Wasserstein Distance: Noisy Score and Optimal Bounds
Denoising diffusion models achieve Wasserstein-2 sampling error of order √D/K up to logarithmic factors for a broad class of distributions, matching the Gaussian lower bound, and score-evaluation noise vanishes as the...
-
Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis
Score stability bounds the generalization gap of diffusion models, identifying early stopping, coarse discretization, and SGD noise as sources of implicit regularization.
-
Fast Convergence for High-Order ODE Solvers in Diffusion Probabilistic Models
A TV convergence bound O(d^{7/4} ε^{1/2} + d(dH)^p) is proved for p-th order (exponential) Runge-Kutta samplers of probability-flow ODEs under C² smoothness of the learned score.
Discussion (0). Sign in to comment.