A Sharp Convergence Theory for The Probability Flow ODEs of Diffusion Models

Documenti analoghi

• Denoising diffusion probabilistic models are optimally adaptive to unknown low dimensionality
  di: Huang, Zhihan, et al.
  Pubblicazione: (2024)
• Dimension-Free Convergence of Diffusion Models for Approximate Gaussian Mixtures
  di: Li, Gen, et al.
  Pubblicazione: (2025)
• Faster Diffusion Models via Higher-Order Approximation
  di: Li, Gen, et al.
  Pubblicazione: (2025)
• Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models
  di: Li, Gen, et al.
  Pubblicazione: (2023)
• A non-asymptotic distributional theory of approximate message passing for sparse and robust regression
  di: Li, Gen, et al.
  Pubblicazione: (2024)