REVIEW 12 cited by
Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion Models
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
Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion Models
read the original 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.
Forward citations
Cited by 12 Pith papers
-
Query Lower Bounds for Diffusion Sampling
Diffusion sampling from d-dimensional distributions requires at least ~sqrt(d) adaptive score queries when score estimates have polynomial accuracy.
-
ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning
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.
-
Lipschitz-Guided Design of Interpolation Schedules in Generative Models
Minimizing averaged squared Lipschitzness of the drift produces interpolation schedules that improve numerical accuracy and mitigate mode collapse in generative models, with closed-form optima for Gaussians and valida...
-
ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning
ART learns adaptive timestep grids for score-based diffusion sampling via continuous-time control and actor-critic RL, yielding higher sample quality than fixed schedules at matched compute while generalizing across b...
-
Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices
For a broad class of coefficients, diffusion models achieve Õ(k/ε) iteration complexity for ε-accurate TV sampling under low-dimensional structure, independent of ambient dimension.
-
Colored Noise Diffusion Sampling
CNS is a plug-and-play stochastic sampler for diffusion models that uses timestep- and frequency-dependent colored noise to allocate energy to unresolved bands, producing lower FID scores than standard ODE/SDE baselin...
-
From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models
GADD achieves O(polylog(ε^{-1})) sampling complexity for uniform-rate discrete diffusion models via Gibbs correctors derived from the score function, with supporting experiments on text and music.
-
On the Robustness of Distribution Support under Diffusion Guidance
Guided diffusion generates samples near the target distribution support under exact score access, explaining its empirical success in producing plausible outputs.
-
Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach
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.
-
ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule
ART reparameterizes diffusion sampling time and uses RL to learn optimal timestep schedules that reduce discretization error and improve generation quality across budgets and datasets.
-
On the Robustness of Distribution Support under Diffusion Guidance
Establishes robustness of distribution support for guided diffusion processes under exact score access across DDIM, DDPM, and exponential integrator discretizations.
-
Deep Neural Networks Inspired by Differential Equations
A review of differential-equation-inspired neural networks that compiles known results into a taxonomy, with no new experiments or theory.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.