扩散与对抗性施罗德桥 via 迭代比例马尔可夫拟合
Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian Fitting
AI总结:
本文提出IPMF方法,结合IMF和IPF解决施罗德桥问题,实现图像生成与翻译任务中的平衡优化。
摘要:
迭代马尔可夫拟合(IMF)过程通过迭代地将投影到马尔可夫过程空间和反向类中,成功解决了施罗德桥(SB)问题。然而,实际应用中需要一种启发式修改——在每次迭代中交替拟合正向和反向时间扩散。这种修改对于稳定训练和在如无配域翻译等应用中获得可靠结果至关重要。我们的工作揭示了修改后的IMF与迭代比例拟合(IPF)过程之间的紧密联系——这是SB问题的基础方法,也称为Sinkhorn算法。具体来说,我们证明了IMF的启发式修改有效地结合了IMF和IPF过程。我们将这种综合方法称为迭代比例马尔可夫拟合(IPMF)过程。通过理论和实证分析,我们建立了IPMF过程在各种设置下的收敛性,为解决SB问题开发了统一的框架。此外,从实际角度来看,IPMF过程能够灵活地在图像相似性和生成质量之间进行权衡,提供了一种新的机制来定制模型以适应特定任务。
英文摘要:
The Iterative Markovian Fitting (IMF) procedure, which iteratively projects onto the space of Markov processes and the reciprocal class, successfully solves the Schrödinger Bridge (SB) problem. However, an efficient practical implementation requires a heuristic modification -- alternating between fitting forward and backward time diffusion at each iteration. This modification is crucial for stabilizing training and achieving reliable results in applications such as unpaired domain translation. Our work reveals a close connection between the modified version of IMF and the Iterative Proportional Fitting (IPF) procedure -- a foundational method for the SB problem, also known as Sinkhorn's algorithm. Specifically, we demonstrate that the heuristic modification of the IMF effectively integrates both IMF and IPF procedures. We refer to this combined approach as the Iterative Proportional Markovian Fitting (IPMF) procedure. Through theoretical and empirical analysis, we establish the convergence of the IPMF procedure under various settings, contributing to developing a unified framework for solving SB problems. Moreover, from a practical standpoint, the IPMF procedure enables a flexible trade-off between image similarity and generation quality, offering a new mechanism for tailoring models to specific tasks.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。