paper-with-me

홈 › Papers

Quotient Geometry and Persistence-Stable Metrics for Swarm Configurations

2026-03-14 · Mark M. Bailey arxiv

Swarm and constellation reconfiguration can be viewed as motion of an unordered point configuration in an ambient space. Here, we provide persistence-stable, symmetry-invariant geometric representations for comparing and monitoring multi-agent configuration data. We introduce a quotient formation space $\mathcal{S}_n(M,G)=M^n/(G\times S_n)$ and a formation matching metric $d_{M,G}$ obtained by optimizing a worst-case assignment error over ambient symmetries $g\in G$ and relabelings $σ\in S_n$. This metric is a structured, physically interpretable relaxation of Gromov--Hausdorff distance: the induced inter-agent metric spaces satisfy $d_{\mathrm{GH}}(X_x,X_y)\le d_{M,G}([x],[y])$. Composing this bound with stability of Vietoris--Rips persistence yields $d_B(Φ_k([x]),Φ_k([y]))\le d_{M,G}([x],[y])$, providing persistence-stable signatures for reconfiguration monitoring. We analyze the metric geometry of $(\mathcal{S}_n(M,G),d_{M,G})$: under compactness/completeness assumptions on $M$ and compact $G$ it is compact/complete and the metric induces the quotient topology; if $M$ is geodesic then the quotient is geodesic and exhibits stratified singularities along collision and symmetry strata, relating it to classical configuration spaces. We study expressivity of the signatures, identifying symmetry-mismatch and persistence-compression mechanisms for non-injectivity. Finally, in a phase-circle model we prove a conditional inverse theorem: under semicircle support and a gap-labeling margin, the $H_0$ signature is locally bi-Lipschitz to $d_{M,G}$ up to an explicit factor, yielding two-sided control. Examples on $\mathbb{S}^2$ and $\mathbb{T}^m$ illustrate satellite-constellation and formation settings.

📄 PDF Abstract BibTeX arXiv:2603.18041

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Metrics for Learning in Topological Persistence

2019-06-11 · Henri Riihimäki, José Licón-Saláiz

Persistent homology analysis provides means to capture the connectivity structure of data sets in various dimensions. On the mathematical level, by defining a metric between the objects that persistence attaches to data …

General Classification

Manifold Learning in Quotient Spaces

2018-06-01 · CVPR 2018 6 · Éloi Mehr, André Lieutier, Fernando Sanchez Bermudez, Vincent Guitteny 외

When learning 3D shapes we are usually interested in their intrinsic geometry rather than in their orientation. To deal with the orientation variations the usual trick consists in augmenting the data to exhibit all possi…

From Geometry to Topology: Inverse Theorems for Distributed Persistence

2021-01-28 · Elchanan Solomon, Alexander Wagner, Paul Bendich

What is the "right" topological invariant of a large point cloud X? Prior research has focused on estimating the full persistence diagram of X, a quantity that is very expensive to compute, unstable to outliers, and far …

Quotient Geometry, Effective Curvature, and Implicit Bias in Simple Shallow Neural Networks

2026-03-23 · Hang-Cheng Dong, Pengcheng Cheng arxiv

Overparameterized shallow neural networks admit substantial parameter redundancy: distinct parameter vectors may represent the same predictor due to hidden-unit permutations, rescalings, and related symmetries. As a resu…

Persistent Classification: A New Approach to Stability of Data and Adversarial Examples

2024-04-11 · Brian Bell, Michael Geyer, David Glickenstein, Keaton Hamm 외

There are a number of hypotheses underlying the existence of adversarial examples for classification problems. These include the high-dimensionality of the data, high codimension in the ambient space of the data manifold…