arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2507.03065cs.LG
收藏

持久同调作为涌现结构理论

Persistent Homology as a Theory of Emergent Structure

Department of Computer Science, University at Albany(计算机科学系,阿尔巴尼大学)

Xin Li

AI总结:

提出将涌现属性定义为持久非平凡同调类,通过持久条、收缩相似图算子和Hodge分解等工具,统一描述涌现的六个特征,并提供可验证预测。

摘要:

为什么某些宏观结构在其微观组分不断变化时仍保持可识别?涡旋在流体团翻转时持续,神经记忆在尖峰和突触波动时持续,机构在个体进出时持续。我们提出一个尺度相对的回答:涌现属性是一个持久的非平凡同调类 $[z]\in H_p=\ker\partial_p/\im\partial_{p+1}$,即一个在描述过滤中闭合但不精确的宏观特征。这一识别将涌现转化为一个\emph{测量}问题。持久条检测稳定的宏观特征,我们引入收缩相似(CS)图算子以提供预测鲁棒性的支架谱间隙。Hodge分解将调和宏观支架与精确和共精确微观流分离;函子凝聚解释何时一个层次的涌现类成为下一个层次的单位。由此产生的支架-流框架用同一数学语言表达了涌现的六个熟悉特征(即必然性、相干性、不可约性、互补性、鲁棒性和层次性)。它还在大气、神经和社会系统中产生可证伪的预测:真正的涌现结构应在过滤中持续,保持谱稳定,对调和干预有不成比例的反应,并需要时间尺度分离以实现层次自主性。

英文摘要:

Why do some macroscopic structures remain identifiable even though their microscopic constituents continually change? Vortices persist while fluid parcels turn over, neural memories persist while spikes and synapses fluctuate, and institutions persist while individuals enter and leave. We propose a scale-relative answer: an emergent property is a persistent nontrivial homology class [z]\in H_p=\ker\partial_p/\im\partial_{p+1}, a macro-feature that is closed but not exact across a filtration of descriptions. This identification turns emergence into a \emph{measurement} problem. Persistent bars detect stable macro-features, and we introduce a contractive-similarity (CS) graph operator to supply scaffold spectral gaps that predict robustness. Hodge decomposition separates harmonic macro-scaffold from exact and co-exact micro-flow; and functorial condensation explains when one level's emergent class becomes a unit for the next. The resulting scaffold-flow framework expresses six familiar signatures of emergence (i.e., inevitability, coherence, irreducibility, complementarity, robustness, and hierarchy) within one mathematical language. It also yields falsifiable predictions across atmospheric, neural, and social systems: genuine emergent structures should persist across filtrations, remain spectrally stable, respond disproportionately to harmonic interventions, and require timescale separation for hierarchical autonomy. We will also discuss the implications of structural persistence for AGI and ASI.

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。

↑