Diffusion sampling from d-dimensional distributions requires at least ~sqrt(d) adaptive score queries when score estimates have polynomial accuracy.
arXiv preprint arXiv:2410.04760 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
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 validation on stochastic PDEs.
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 baselines on ImageNet-256.
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.
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.
Establishes robustness of distribution support for guided diffusion processes under exact score access across DDIM, DDPM, and exponential integrator discretizations.
citing papers explorer
-
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.
-
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 baselines on ImageNet-256.
-
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.
-
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.