Pith. sign in

REVIEW 19 cited by

Convergence of denoising diffusion models under the manifold hypothesis

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

arxiv 2208.05314 v2 pith:7GA6475C submitted 2022-08-10 stat.ML cs.LGmath.PR

Convergence of denoising diffusion models under the manifold hypothesis

classification stat.ML cs.LGmath.PR
keywords modelsdistributiondiffusiontargetdensityconvergencedenoisingempirical
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Denoising diffusion models are a recent class of generative models exhibiting state-of-the-art performance in image and audio synthesis. Such models approximate the time-reversal of a forward noising process from a target distribution to a reference density, which is usually Gaussian. Despite their strong empirical results, the theoretical analysis of such models remains limited. In particular, all current approaches crucially assume that the target density admits a density w.r.t. the Lebesgue measure. This does not cover settings where the target distribution is supported on a lower-dimensional manifold or is given by some empirical distribution. In this paper, we bridge this gap by providing the first convergence results for diffusion models in this more general setting. In particular, we provide quantitative bounds on the Wasserstein distance of order one between the target data distribution and the generative distribution of the diffusion model.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. An exact information theory of generalization phase transitions in Bayesian diffusion models

    cs.LG 2026-07 conditional novelty 8.0

    Bayesian diffusion models memorize training data when mutual information between restricted observations and training data exceeds log dataset size, and generalize otherwise.

  2. Asymptotic-Preserving A Posteriori Analysis of Diffusion and Flow-Matching Samplers

    cs.LG 2026-07 accept novelty 7.5

    DDIM (σ-clock Euler) is the unique layer-exact fixed-step sampler; deterministic residual budgets stay O(1) with no log(1/σ_min), while stochastic path-KL scales as Λ²/N from the Itô term alone.

  3. Let EEG Models Learn EEG

    cs.CV 2026-05 unverdicted novelty 7.0

    JET is a conditional flow matching framework that generates EEG as continuous raw sequences with added constraints for spectral and temporal properties, achieving over 40% lower TS-FID than prior discrete denoising me...

  4. Training-Free Generative Sampling via Moment-Matched Score Smoothing

    stat.ML 2026-05 unverdicted novelty 7.0

    MM-SOLD is a training-free particle sampler whose large-particle limit converges to a moment-matched Gibbs distribution obtained by exponentially tilting a score-smoothed target.

  5. Proximal-Based Generative Modeling for Bayesian Inverse Problems

    math.OC 2026-05 unverdicted novelty 7.0

    PGM replaces the intractable likelihood score in diffusion models with a closed-form Moreau score computed via proximal operators, enabling non-asymptotic sampling for inverse problems trained only on prior data.

  6. Proximal-Based Generative Modeling for Bayesian Inverse Problems

    math.OC 2026-05 unverdicted novelty 7.0

    PGM framework links diffusion to proximal regularization for closed-form Moreau-score sampling in Bayesian inverse problems, learned only from prior samples.

  7. The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives

    cs.LG 2026-05 unverdicted novelty 7.0

    The choice of closeness measure in diffusion reward alignment determines the computational primitives and tractable reward classes, with linear exponential tilts sufficing for KL with convex rewards and proximal oracl...

  8. Geometry-Aware Discretization Error of Diffusion Models

    cs.LG 2026-05 unverdicted novelty 7.0

    First-order asymptotic expansions of weak and Fréchet discretization errors in diffusion sampling are derived, explicit under Gaussian data through covariance geometry and robust to other data geometries.

  9. Diffusion Processes on Implicit Manifolds

    cs.LG 2026-04 unverdicted novelty 7.0

    Implicit Manifold-valued Diffusions (IMDs) are data-driven SDEs built from proximity graphs that converge in law to smooth manifold diffusions as sample count increases.

  10. Diffusion Processes on Implicit Manifolds

    cs.LG 2026-04 unverdicted novelty 7.0

    Defines diffusion processes on implicit data manifolds via proximity-graph approximations to the infinitesimal generator and carré-du-champ operator, proves convergence in law to the continuous manifold process, and p...

  11. Structured drift design for denoising diffusion models

    math.ST 2026-06 conditional novelty 6.0

    A variance-aware anisotropic OU drift keeps multimodal and correlated structure longer in diffusion, and bounds reverse initialization error by local cluster variance rather than global variance.

  12. Noise Schedule Design for Diffusion Models: An Optimal Control Perspective

    cs.LG 2026-05 unverdicted novelty 6.0

    Recasting diffusion noise schedule design as optimal control on Fisher information yields sufficient conditions for O(d/n) sampling error and parametric closed-form schedules that generalize exponential/sigmoid ones a...

  13. Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity

    cs.LG 2026-03 unverdicted novelty 6.0

    Diffusion models on manifold-supported data admit score decompositions whose statistical rates are controlled by intrinsic dimension and curvature.

  14. Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation

    stat.ML 2026-05 unverdicted novelty 5.0

    Diffusion-based denoising score matching avoids the mode-separation degradation that affects vanilla score matching error bounds, via suitable hyperparameter choice.

  15. On the Regularity and Generalization of One-Step Wasserstein-guided Generative Models for PDE-Induced Measures

    cs.LG 2026-05 unverdicted novelty 5.0

    The paper proves Hölder continuity of optimal transport maps for PDE-induced measures via doubling conditions and derives excess-risk bounds for one-step generative models like DeepParticle.

  16. On the Limits of Latent Reuse in Diffusion Models

    stat.ML 2026-05 unverdicted novelty 5.0

    Reusing source latent spaces in diffusion models under distribution shift produces target score error set by principal-angle misalignment and diffusion-time-amplified ambient noise.

  17. Structured drift design for denoising diffusion models

    math.ST 2026-06 unverdicted novelty 4.0

    Proposes GOU process with anisotropic drift to embed data geometry in diffusion models, claiming better mode separation, correlation preservation, and convergence than isotropic baselines.

  18. Statistical Properties of Training & Generalization

    stat.ML 2026-06 unverdicted novelty 2.0

    Neural scaling laws in deep learning interact with physics constraints and inductive biases beyond classical statistics.

  19. Statistical Properties of Training & Generalization

    stat.ML 2026-06 unverdicted novelty 1.0

    Review of neural scaling laws and their relation to constraints and inductive biases when applying machine learning to physics problems.