Incorporating Pre-trained Diffusion Models in Solving the Schrödinger Bridge Problem
By: Zhicong Tang , Tiankai Hang , Shuyang Gu and more
Potential Business Impact:
Makes AI create better pictures faster.
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.
Similar Papers
Multi-Marginal Schrödinger Bridge Matching
Machine Learning (Stat)
Tracks how things change over time.
Exponential Convergence Guarantees for Iterative Markovian Fitting
Machine Learning (Stat)
Makes computer models learn faster and better.
A Closed-Form Diffusion Model for Learnring Dynamics from Marginal Observations
Computation
Creates better AI for images and biology.