Guan-Ding Yu

Convergence of Denoising Diffusion Probabilistic Models: A R\'{e}nyi Divergence Perspective

Denoising diffusion probabilistic models (DDPMs) have emerged as a powerful framework for generative modeling by transforming standard Gaussian inputs into outputs that approximate a target distribution. While DDPMs have been proved to converge in total variation, KL divergence, and Wasserstein distance, these discrepa...