arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.29675cs.LGcond-mat.dis-nnstat.ML
收藏

I-BBS:使用随机距离矩阵理论的潜在子流形无坐标推断

I-BBS: Coordinate-Free Inference of Latent Sub-Manifolds Using Random Distance Matrix Theory

Claude Code

Igor Halperin

AI总结:

提出I-BBS方法,从高维距离矩阵中无坐标推断低维潜在子流形,利用整数稳定特征(多重性和参数无关定律)在噪声下恢复流形维度,无需访问高维向量空间。

摘要:

Bogomolny、Bohigas和Schmit(BBS)发现,从光滑d维流形上采样的N个点的成对距离矩阵的谱编码了底层几何的签名。我们开发了I-BBS(推断-BBS),一种无坐标方法,仅从高维环境距离矩阵中识别嵌入的低维潜在子流形,而无需访问高维向量空间。因此,即使该空间仅部分可观测或未定义,该方法也适用。我们通过两类生成噪声(基于模型和无模型)对环境嵌入进行建模。噪声将潜在信号与流形外成分混合,因此特征值集体重组,无法逐个特征值读取潜在几何。相反,我们从两个在噪声中存活的整数稳定签名中恢复它:顶部非Perron多重态的重数(确定$d$)以及一个无参数定律,描述多重态位置如何随噪声增长而收缩。在合成球面$S^1$、$S^2$和$S^3$上,这些整数签名在噪声下比连续谱斜率稳定得多,盲测从单个距离矩阵中同时恢复了流形和噪声模型。对神经网络表示和动态训练机制的应用在两篇配套论文中展开。

英文摘要:

Bogomolny, Bohigas and Schmit (BBS) found that the spectrum of the pairwise distance matrix on N points sampled from a smooth d-dimensional manifold encodes a signature of the underlying geometry. We develop I-BBS (Inference-BBS), a coordinate-free method that identifies a low-dimensional latent sub-manifold embedded in a high-dimensional ambient distance matrix alone, without accessing an ambient high-dimensional vector space. It therefore applies even when that space is only partly observable or undefined. We model the ambient embedding by two classes of generative noise, model-based and model-free. The noise mixes the latent signal with off-manifold components, so the eigenvalues reorganise collectively and the latent geometry cannot be read off eigenvalue by eigenvalue. We recover it instead from two integer-stable signatures that survive the noise: the multiplicity of the top non-Perron multiplet, which fixes $d$, and a parameter-free law for how the multiplet positions shrink as the noise grows. On synthetic spheres $S^1$, $S^2$ and $S^3$ these integer signatures are far more stable under noise than the continuous spectral slope, and a blind test recovers both the manifold and the noise model from a single distance matrix. Applications to neural-network representations and to the dynamic training regime are developed in two companion papers.

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。

↑