Noising-Denoising by Large Temperature Schr\"{o}dinger Bridges

Abstract

In this note, we establish a connection between denoising diffusion models and large temperature dynamic Schr\"{o}dinger bridges computed with respect to certain reference processes. In particular, we show that in the large temperature regime (i.e. $T \to +\infty$), the Schr\"{o}dinger bridge behaves like a forward time diffusion process over the time interval $[0,T/2]$, and approximately like the time reversal of a diffusion process over $[T/2,T]$. This construction provides a process-level characterization of the gradient flow approximation developed by Clerc et al. (2023).