Year: 2026
Type: preprint
Abstract: In this note, we establish a connection between denoising diffusion models and large temperature dynamic Schrödinger bridges computed with respect to certain reference processes. In particular, we show that in the large temperature regime (i.e. $T \to +\infty$), the Schrödinger 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).
Source: arXiv (Cornell University)
Author: Mulcahy, Garrett
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: National Science Foundation
OpenAlex ID: W7204490259