Understanding Diffusion Models by Feynman's Path Integral

arXiv:2403.11262v1 Announce Type: new
Abstract: Score-based diffusion models have proven effective in image generation and have gained widespread usage; however, the underlying factors contributing to the performance disparity between stochastic and deterministic (i.e., the probability flow ODEs) sampling schemes remain unclear. We introduce a novel formulation of diffusion models using Feynman's path integral, which is a formulation originally developed for quantum physics. We find this formulation providing comprehensive descriptions of score-based generative models, and demonstrate the derivation of backward stochastic …

abstract arxiv cond-mat.stat-mech cs.ai cs.lg diffusion diffusion models feynman flow hep-th however image image generation integral novel path performance probability sampling stochastic type understanding usage