用预训练扩散模型加速并稳定薛定谔桥生成模型的训练
Incorporating Pre-trained Diffusion Models in Solving the Schrödinger Bridge Problem
- 通过三种重参数化技术提升薛定谔桥模型训练速度与稳定性
- 利用预训练扩散模型初始化，显著改善生成性能
- 适合想融合生成模型优势的研究者参考
本文通过三种重参数化技术——迭代比例均值匹配（IPMM）、迭代比例终点匹配（IPTM）和迭代比例流匹配（IPFM），将基于得分的生成模型（即扩散模型）与薛定谔桥（SB）问题统一。这些方法显著加速并稳定了基于SB模型的训练过程。此外，论文提出新的初始化策略，利用预训练的得分生成模型来有效训练基于SB的模型。通过将扩散模型作为初始化起点，同时发挥两类模型的优势，不仅确保了基于SB模型的高效训练，还进一步提升了扩散模型的生成性能。大量实验验证了所提方法的有效性与改进效果。我们相信该工作为未来生成模型研究提供了重要基础。
原文摘要 · Abstract (English)
This paper aims to unify Score-based Generative Models (SGMs), also known as Diffusion models, and the Schrödinger 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。