A note on connections between the Föllmer process and the denoising diffusion probabilistic model
Researchers have explored the connection between Föllmer processes and denoising diffusion probabilistic models (DDPMs), finding that discretizing Föllmer processes can yield optimal hyper-parameter settings for DDPM samplers. This approach has led to improved error bounds in terms of Wasserstein distance and KL divergence. Additionally, a new method called Forward-Learned Discrete Diffusion (FLDD) has been proposed, which learns the noising process to enable faster, few-step generation of high-quality samples. AI
IMPACT Advances in diffusion model theory and sampling techniques could lead to more efficient and higher-quality generative AI.