Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition Diffusion

Documenti analoghi

• Faster Sampling without Isoperimetry via Diffusion-based Monte Carlo
  di: Huang, Xunpeng, et al.
  Pubblicazione: (2024)
• An Improved Analysis of Langevin Algorithms with Prior Diffusion for Non-Log-Concave Sampling
  di: Huang, Xunpeng, et al.
  Pubblicazione: (2024)
• Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
  di: Huang, Xunpeng, et al.
  Pubblicazione: (2024)
• On the $ε$-Free Inference Complexity of Absorbing Discrete Diffusion
  di: Huang, Xunpeng, et al.
  Pubblicazione: (2025)
• Faster Sampling via Stochastic Gradient Proximal Sampler
  di: Huang, Xunpeng, et al.
  Pubblicazione: (2024)