arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.01416cs.LG
收藏

类别型薛定谔桥匹配

Categorical Schrödinger Bridge Matching

Grigoriy Ksenofontov, Alexander Korotin

AI总结:

本文针对离散空间中的薛定谔桥问题,提出类别型薛定谔桥匹配(CSBM)算法,并从理论上证明了离散时间迭代马尔可夫拟合的收敛性,在合成数据和图像VQ表示上验证了其有效性。

摘要:

薛定谔桥(SB)是解决生成建模任务(如非配对域翻译)的强大框架。大多数SB相关研究集中于连续数据空间$\mathbb{R}^{D}$,而在离散数据(例如有限空间$\mathbb{S}^{D}$)上应用SB方法的理论和算法问题仍未解决。此类集合$\mathbb{S}$的典型例子包括现代自编码器的向量量化(VQ)表示码本、文本中的token、分子中原子的类别等。本文利用最近提出的迭代马尔可夫拟合(IMF)过程,为在离散空间中求解SB提供了理论和算法基础。具体而言,我们从理论上证明了离散时间IMF(D-IMF)在离散空间中收敛到SB。这使我们能够开发一种实用的SB计算算法,我们称之为类别型薛定谔桥匹配(CSBM)。我们通过一系列使用合成数据和图像VQ表示的实验展示了CSBM的性能。CSBM的代码可在https://github.com/gregkseno/csbm获取。

英文摘要:

The Schrödinger Bridge (SB) is a powerful framework for solving generative modeling tasks such as unpaired domain translation. Most SB-related research focuses on continuous data space $\mathbb{R}^{D}$ and leaves open theoretical and algorithmic questions about applying SB methods to discrete data, e.g, on finite spaces $\mathbb{S}^{D}$. Notable examples of such sets $\mathbb{S}$ are codebooks of vector-quantized (VQ) representations of modern autoencoders, tokens in texts, categories of atoms in molecules, etc. In this paper, we provide a theoretical and algorithmic foundation for solving SB in discrete spaces using the recently introduced Iterative Markovian Fitting (IMF) procedure. Specifically, we theoretically justify the convergence of discrete-time IMF (D-IMF) to SB in discrete spaces. This enables us to develop a practical computational algorithm for SB, which we call Categorical Schrödinger Bridge Matching (CSBM). We show the performance of CSBM via a series of experiments with synthetic data and VQ representations of images. The code of CSBM is available at https://github.com/gregkseno/csbm.

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。

↑