Pith. sign in

REVIEW 10 cited by

Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2410.04760 v1 pith:MCT54M7P submitted 2024-10-07 stat.ML cs.LG

Yuchen Wu , Yuxin Chen , Yuting Wei This is my paper · ORCID
classification stat.MLcs.LG
keywords diffusionvarepsilonaccelerationmodelsproposedstochasticevaluationsfunction
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Diffusion models play a pivotal role in contemporary generative modeling, claiming state-of-the-art performance across various domains. Despite their superior sample quality, mainstream diffusion-based stochastic samplers like DDPM often require a large number of score function evaluations, incurring considerably higher computational cost compared to single-step generators like generative adversarial networks. While several acceleration methods have been proposed in practice, the theoretical foundations for accelerating diffusion models remain underexplored. In this paper, we propose and analyze a training-free acceleration algorithm for SDE-style diffusion samplers, based on the stochastic Runge-Kutta method. The proposed sampler provably attains $\varepsilon^2$ error -- measured in KL divergence -- using $\widetilde O(d^{3/2} / \varepsilon)$ score function evaluations (for sufficiently small $\varepsilon$), strengthening the state-of-the-art guarantees $\widetilde O(d^{3} / \varepsilon)$ in terms of dimensional dependency. Numerical experiments validate the efficiency of the proposed method.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

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

  1. ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning

    cs.LG 2026-07 unverdicted novelty 7.0 of 10

    ART-RL learns adaptive diffusion sampling timesteps via continuous-time control and Gaussian actor–critic RL, improving and transferring over hand-designed grids at matched budgets.

  2. 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.

  3. Assessing the Quality of Denoising Diffusion Models in Wasserstein Distance: Noisy Score and Optimal Bounds

    stat.ML 2025-06 conditional novelty 7.0 of 10

    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...

  4. Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach

    cs.AI 2026-02 conditional novelty 6.0 of 10

    By adding drift g(t)^2 ∇log h(t,y) with h estimated via martingale and covariation losses, diffusion samples can be hard-conditioned on an event.

  5. Analysis of Langevin midpoint methods using an anticipative Girsanov theorem

    math.NA 2025-07 conditional novelty 6.0 of 10

    A Malliavin-calculus Girsanov analysis yields process-level KL and Rényi bounds for midpoint Langevin discretizations and a O~(kappa^{5/4} d^{1/4}/epsilon^{1/2}) query complexity for a new deterministic double midpoin...

  6. Fast Convergence for High-Order ODE Solvers in Diffusion Probabilistic Models

    cs.LG 2025-06 conditional novelty 6.0 of 10

    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.

  7. Advancing Wasserstein Convergence Analysis of Score-Based Models: Insights from Discretization and Second-Order Acceleration

    stat.ML 2025-02 conditional novelty 6.0 of 10

    A second-order local linearization sampler is shown to reach O~(1/ε) Wasserstein-2 accuracy for strongly log-concave score-based diffusion models, improving on the O~(1/ε²) rate of Euler and exponential integrator schemes.

  8. Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A weighted-particle sampler evolves the posterior through the diffusion model's reverse dynamics, with theoretical error bounds and improved image reconstructions.

  9. Information-Theoretic Proofs for Diffusion Sampling

    stat.ML 2025-02 accept novelty 5.0 of 10

    Using information-theoretic identities, the authors prove non-asymptotic KL bounds for discrete-time diffusion sampling and show that matching higher moments accelerates convergence.

  10. Deep Neural Networks Inspired by Differential Equations

    cs.LG 2025-10 unverdicted

    A review of differential-equation-inspired neural networks that compiles known results into a taxonomy, with no new experiments or theory.

Pith tools