Guardado en:
Detalles Bibliográficos
Autores principales: Trentini, Bruno, Hume, Jacob, Isoldi, Vincenzo Antonio, Misof, Philipp, Ivshina, Ekaterina S., Maggs, Kelly
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.15524
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914568783003648
author Trentini, Bruno
Hume, Jacob
Isoldi, Vincenzo Antonio
Misof, Philipp
Ivshina, Ekaterina S.
Maggs, Kelly
author_facet Trentini, Bruno
Hume, Jacob
Isoldi, Vincenzo Antonio
Misof, Philipp
Ivshina, Ekaterina S.
Maggs, Kelly
contents Point cloud learning often rests on the premise that observed samples are noisy traces of an underlying geometric object, such as a manifold embedded in a high-dimensional feature space. Yet much of this geometry is not captured directly by coordinates, pairwise distances, or learned graph neighborhoods alone. In the smooth setting, differential forms are devices to encode higher order tangency information. In this work, we introduce a new family of principled learnable geometric features for point clouds called neural point-forms (NPFs). In the absence of a natural tangency structure, we instead use Laplacian-based techniques from Diffusion Geometry to build a discrete model for comparing differential forms on point clouds via inner products. In the continuum, submanifolds of a shared ambient feature space are represented as comparison matrices, whose entries describe how pairs of feature forms interact with extrinsic tangency information. We make this intuition precise by proving the long-run consistency of comparison matrices under standard sampling, bandwidth, density, and manifold-hypothesis assumptions. This yields a compact, efficient and permutation-invariant neural layer whose output is a learned form-comparison matrix. Across synthetic and biologically relevant experiments, we show that NPFs provide a competitive, and interpretable representation, with the strongest benefits appearing when labels depend on sampling density, manifold-like structure, or response-relevant population geometry.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15524
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neural Point-Forms
Trentini, Bruno
Hume, Jacob
Isoldi, Vincenzo Antonio
Misof, Philipp
Ivshina, Ekaterina S.
Maggs, Kelly
Machine Learning
Artificial Intelligence
Differential Geometry
Statistics Theory
68T07 (Primary) 68T05, 68T09, 58A10, 53C21, 53C23, 58J50, 58J65, 62R30, 62G07, 92B20 (Secondary)
I.2.0; I.2.6; I.5.1; G.3; G.1.3; J.3
Point cloud learning often rests on the premise that observed samples are noisy traces of an underlying geometric object, such as a manifold embedded in a high-dimensional feature space. Yet much of this geometry is not captured directly by coordinates, pairwise distances, or learned graph neighborhoods alone. In the smooth setting, differential forms are devices to encode higher order tangency information. In this work, we introduce a new family of principled learnable geometric features for point clouds called neural point-forms (NPFs). In the absence of a natural tangency structure, we instead use Laplacian-based techniques from Diffusion Geometry to build a discrete model for comparing differential forms on point clouds via inner products. In the continuum, submanifolds of a shared ambient feature space are represented as comparison matrices, whose entries describe how pairs of feature forms interact with extrinsic tangency information. We make this intuition precise by proving the long-run consistency of comparison matrices under standard sampling, bandwidth, density, and manifold-hypothesis assumptions. This yields a compact, efficient and permutation-invariant neural layer whose output is a learned form-comparison matrix. Across synthetic and biologically relevant experiments, we show that NPFs provide a competitive, and interpretable representation, with the strongest benefits appearing when labels depend on sampling density, manifold-like structure, or response-relevant population geometry.
title Neural Point-Forms
topic Machine Learning
Artificial Intelligence
Differential Geometry
Statistics Theory
68T07 (Primary) 68T05, 68T09, 58A10, 53C21, 53C23, 58J50, 58J65, 62R30, 62G07, 92B20 (Secondary)
I.2.0; I.2.6; I.5.1; G.3; G.1.3; J.3
url https://arxiv.org/abs/2605.15524