arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.07591math.AT
收藏

局部拉普拉斯:数据分析的理论与模型

Local Laplacian: theory and models for data analysis

Mathematical Science Research Center, Chongqing University of Technology(重庆理工大学数学科学研究中心);Department of Mathematics and Statistics, University of North Carolina at Charlotte(北卡罗来纳大学夏洛特分校数学与统计系)

Jian Liu, Hongsong Feng, Kefeng Liu

AI总结:

本文提出持续局部拉普拉斯方法,通过理论推导和算法设计,解决拓扑数据分析中局部结构敏感性和计算成本高的问题,实现高效并行计算。

摘要:

尽管拓扑数据分析已发展为一种强大的结构推断范式,但其基础工具,特别是持续同调和持续拉普拉斯,往往对局部结构波动不敏感,并且在大规模数据集上计算成本过高。为弥补这一差距,我们引入了持续局部拉普拉斯形式化方法,旨在提取细粒度的局部拓扑和几何特征,同时启用高效且可并行化的计算流程。在理论方面,我们证明了一个广义的持续霍奇同构,确立了持续局部拉普拉斯的调和空间与持续局部同调是同构的。此外,我们推导了持续局部拉普拉斯与其对应链接复形在移位维度下的单位等价性。这种谱共轭性为开发高效的计算方案来解决持续局部谱不变量奠定了数学基础。我们进一步将这一构造扩展到点云和图结构数据,通过组合滤泡来表征其持续局部谱特性。所得到的架构本质上是解耦的,有助于大规模并行化,并使其在大规模网络分析和分布式计算环境中有独特的可扩展性。

英文摘要:

While topological data analysis has emerged as a powerful paradigm for structural inference, its foundational tools, notably persistent homology and the persistent Laplacian, are frequently insensitive to localized structural fluctuations and suffer from prohibitive computational costs on large-scale datasets. To bridge this gap, we introduce the persistent local Laplacian formalism, which is designed to extract fine-grained local topological and geometric signatures while enabling a highly efficient, parallelizable computational workflow. On the theoretical front, we prove a generalized persistent Hodge isomorphism, establishing that the harmonic space of the persistent local Laplacian is isomorphic to the persistent local homology. Furthermore, we derive a unitary equivalence between the persistent local Laplacian and the persistent Laplacian of its corresponding link complex at a shifted dimension. This spectral conjugacy establishes the mathematical foundation for developing efficient computational schemes to resolve persistent local spectral invariants. We further extend this construction to point clouds and graph-structured data, characterizing their persistent local spectral properties through combinatorial filtrations. The resulting architecture is inherently decoupled, facilitating massive parallelization and rendering it uniquely scalable for large-scale network analysis and distributed computational environments.

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。

↑