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 2602.09058stat.MLcs.AIcs.ITcs.LGmath.IT
收藏

持久熵作为相变检测器

Persistent Entropy as a Detector of Phase Transitions

Marcos Gutierrez-del-Pozo, Eduardo Paluzo-Hidalgo, Matteo Rucco

AI总结:

本文提出基于拓扑稳定化的框架,利用持久熵检测相变,通过理论分析和实验验证其在不同数据集中的有效性。

摘要:

持久熵(PE)是持久条形码的信息论汇总统计量,已被广泛用于检测复杂系统中的状态变化。尽管在经验上取得了成功,但对何时以及为何持久熵能可靠地检测相变的普遍理论理解仍然有限,尤其是在随机和数据驱动的设置中。在本工作中,我们建立了一个通用、模型无关的定理,提供了持久熵能够区分两个相的充分条件。我们证明持久熵在相之间表现出渐近非消失的差距。该结果仅依赖于持久熵沿收敛图序列的连续性,或者在轻微正则化下,因此可以广泛应用于各种数据模态、滤波器和同调次数。为了将渐近理论与有限时间计算联系起来,我们引入了一个基于拓扑稳定化的操作框架,定义了一个拓扑转变时间,通过在滑动窗口内稳定选定的拓扑统计量来定义,并在有限的观测时间范围内定义一个基于概率的临界参数估计器。我们验证了该框架在库莫特同步转变、维克塞克集体运动中的有序到无序转变以及神经网络训练动态等多个数据集和架构上的有效性。在所有实验中,持久熵的稳定性和在不同实现中的变异性崩溃提供了稳健的数值特征,与理论机制一致。

英文摘要:

Persistent entropy is a scalar summary of persistence barcodes widely used to detect regime changes, yet there is no account of when a structural change in a barcode must produce a detectable change in entropy. We establish a model-agnostic theorem supplying such conditions. Treating persistence diagrams as random objects indexed by a control parameter, we identify a dispersion-condensation mechanism in the normalized persistence weights and derive an explicit lower bound on the entropy difference between the two regimes, valid with high probability at finite sample size and insensitive to the absolute scale of bar lifetimes. We also give a procedure for verifying the hypotheses on empirical barcodes. Applied to convolutional networks, the criterion shows that the circular organization of learned filters reported by Gabrielsson and Carlsson emerges through a sharp topological phase transition, and locates its onset: within a few hundred iterations on MNIST, but an order of magnitude later on CIFAR-10. The same criterion detects the Kuramoto synchronization and Vicsek order-disorder transitions.

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。

↑