Pith. sign in

REVIEW 8 cited by

The probability flow ODE is provably fast

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 2305.11798 v1 pith:BEXK3FY3 submitted 2023-05-19 cs.LG math.STstat.MLstat.TH

classification cs.LGmath.STstat.MLstat.TH
keywords correctorddpmdiffusionflowguaranteesimplementationmodelingprobability
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

We provide the first polynomial-time convergence guarantees for the probability flow ODE implementation (together with a corrector step) of score-based generative modeling. Our analysis is carried out in the wake of recent results obtaining such guarantees for the SDE-based implementation (i.e., denoising diffusion probabilistic modeling or DDPM), but requires the development of novel techniques for studying deterministic dynamics without contractivity. Through the use of a specially chosen corrector step based on the underdamped Langevin diffusion, we obtain better dimension dependence than prior works on DDPM ($O(\sqrt{d})$ vs. $O(d)$, assuming smoothness of the data distribution), highlighting potential advantages of the ODE framework.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Denoising growth complexity: Data geometry and certified schedules for diffusion sampling

    math.ST 2026-07 accept novelty 8.0 of 10

    A new measure, the denoising growth complexity, provides local KL error bounds for Euler diffusion samplers and yields certified, geometry-adaptive schedules.

  2. Low-dimensional adaptation of diffusion models: Convergence in total variation

    stat.ML 2025-01 conditional novelty 8.0 of 10

    Under exact score functions and a covering-number notion of intrinsic dimension, DDIM and DDPM reach TV error epsilon in O-tilde(k/epsilon) iterations.

  3. Fast Score-Based Sampling via Log-Concave Reductions

    math.ST 2025-12 conditional novelty 7.0 of 10

    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.

  4. Faster Diffusion Models via Higher-Order Approximation

    cs.LG 2025-06 conditional novelty 7.0 of 10

    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.

  5. Denoising Data with Measurement Error Using a Reproducing Kernel-based Diffusion Model

    stat.ME 2024-12 conditional novelty 7.0 of 10

    An RKHS-based diffusion denoiser produces samples whose distribution is within O((BK/n)^(1/4)) total variation of the error-free distribution, under normal measurement error.

  6. Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models

    cs.LG 2024-12 conditional novelty 7.0 of 10

    A time-dilation schedule makes the mode-probability learning phase survive in high dimension, and the learned flow autoencoder recovers the mixture's p and σ² in two separate phases.

  7. Adaptivity and Convergence of Probability Flow ODEs in Diffusion Generative Models

    stat.ML 2025-01 conditional novelty 5.0 of 10

    With accurate score estimates, the probability flow ODE sampler reaches O(k/T) total-variation error, where k is the intrinsic dimension of the target distribution.

  8. ProT-GFDM: A Generative Fractional Diffusion Model for Protein Generation

    q-bio.QM 2025-04 conditional novelty 4.0 of 10

    ProT-GFDM swaps Brownian motion for fractional Brownian motion in a score-based diffusion model and reports small gains in density, coverage, and FID when generating 32-residue Cα distance maps.

Pith tools