Diffusion models, which convert noise into new data instances by learning to reverse a
diffusion process, have become a cornerstone in contemporary generative modeling. In this …

The denoising diffusion probabilistic model (DDPM) has emerged as a mainstream
generative model in generative AI. While sharp convergence guarantees have been …

Discrete diffusion models have gained increasing attention for their ability to model complex
distributions with tractable sampling and inference. However, the error analysis for discrete …

Given a distribution P∗ over X, a hypothesis class H, a loss function l: H× X→[0, 1], a prior
distribution π over H, a real number δ∈(0, 1), and a real number λ> 0, with probability at …