Score: 0

Incorporating Pre-trained Diffusion Models in Solving the Schrödinger Bridge Problem

Published: August 25, 2025 | arXiv ID: 2508.18095v1

By: Zhicong Tang , Tiankai Hang , Shuyang Gu and more

Potential Business Impact:

Makes AI create better pictures faster.

Business Areas:
STEM Education Education, Science and Engineering

This paper aims to unify Score-based Generative Models (SGMs), also known as Diffusion models, and the Schr\"odinger Bridge (SB) problem through three reparameterization techniques: Iterative Proportional Mean-Matching (IPMM), Iterative Proportional Terminus-Matching (IPTM), and Iterative Proportional Flow-Matching (IPFM). These techniques significantly accelerate and stabilize the training of SB-based models. Furthermore, the paper introduces novel initialization strategies that use pre-trained SGMs to effectively train SB-based models. By using SGMs as initialization, we leverage the advantages of both SB-based models and SGMs, ensuring efficient training of SB-based models and further improving the performance of SGMs. Extensive experiments demonstrate the significant effectiveness and improvements of the proposed methods. We believe this work contributes to and paves the way for future research on generative models.

Page Count
21 pages

Category
Computer Science:
CV and Pattern Recognition