Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves

• URL: http://arxiv.org/abs/2605.06395v1
• Date: Thu, 07 May 2026 15:08:58 GMT
• Title: Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves
• Abstract summary: We introduce a novel convolutional learning framework for possibly infinite-dimensional signals supported on a manifold.<n>We make HilbNets and, more generally, the convolution operation, implementable via a two-stage sampling procedure.<n>Our results broaden the scope of geometric learning as a whole by lifting classical Laplacian-based frameworks to settings where the signal at each point lives in its own Hilbert space.
• Score: 68.683840670745
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern deep learning architectures increasingly contend with sophisticated signals that are natively infinite-dimensional, such as time series, probability distributions, or operators, and are defined over irregular domains. Yet, a unified learning theory for these settings has been lacking. To start addressing this gap, we introduce a novel convolutional learning framework for possibly infinite-dimensional signals supported on a manifold. Namely, we use the connection Laplacian associated with a Hilbert bundle as a convolutional operator, and we derive filters and neural networks, dubbed as \textit{HilbNets}. We make HilbNets and, more generally, the convolution operation, implementable via a two-stage sampling procedure. First, we show that sampling the manifold induces a Hilbert Cellular Sheaf, a generalized graph structure with Hilbert feature spaces and edge-wise coupling rules, and we prove that its sheaf Laplacian converges in probability to the underlying connection Laplacian as the sampling density increases. Notably, this result is a generalization to the infinite-dimensional bundle setting of the Belkin \& Niyogi \cite{BELKIN20081289} convergence result for the graph Laplacian to the manifold Laplacian, a theoretical cornerstone of geometric learning methods. Second, we discretize the signals and prove that the discretized (implementable) HilbNets converge to the underlying continuous architectures and are transferable across different samplings of the same bundle, providing consistency for learning. Finally, we validate our framework on synthetic and real-world tasks. Overall, our results broaden the scope of geometric learning as a whole by lifting classical Laplacian-based frameworks to settings where the signal at each point lives in its own Hilbert space.

Related papers

• Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks [28.874026012129615]
  Deep neural networks encode complex representations, but deconstructing this internal knowledge remains a challenge.<n>Given the link between learning and compression, network compression offers a promising lens to analyze this knowledge.<n>We introduce Hilbert Operator for Progressive.<n>HOPE, a mathematical framework to gradually deconstruct the representations in trained network weights.
  arXiv  Detail & Related papers  (2026-07-23T14:31:16Z)
• A Universal Banach--Bregman Framework for Stochastic Iterations: Unifying Stochastic Mirror Descent, Learning and LLM Training [8.57419236859437]
  This work introduces a pioneering Banach--Bregman framework for optimization.<n>It establishes Bregman geometry as a foundation for next-generation optimization.<n> Empirical studies across machine learning, deep learning, reinforcement learning, and large language models show up to 20% faster convergence.
  arXiv  Detail & Related papers  (2025-09-17T17:50:59Z)
• Adaptive Riemannian Graph Neural Networks [29.859977834688625]
  We introduce a novel framework that learns a continuous and anisotropic metric tensor field over the graph.<n>It allows each node to determine its optimal local geometry, enabling the model to fluidly adapt to the graph's structural landscape.<n>Our method demonstrates superior performance on both homophilic and heterophilic benchmark geometries.
  arXiv  Detail & Related papers  (2025-08-04T16:55:02Z)
• Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learning [70.0681902472251]
  We propose a novel contrastive learning framework to learn high-quality graph embeddings in hyperbolic space.<n>Specifically, we design the alignment metric that effectively captures the hierarchical data-invariant information.<n>We show that in the hyperbolic space one has to address the leaf- and height-level uniformity related to properties of trees.
  arXiv  Detail & Related papers  (2023-10-27T15:31:42Z)
• Curve Your Attention: Mixed-Curvature Transformers for Graph Representation Learning [77.1421343649344]
  We propose a generalization of Transformers towards operating entirely on the product of constant curvature spaces. We also provide a kernelized approach to non-Euclidean attention, which enables our model to run in time and memory cost linear to the number of nodes and edges.
  arXiv  Detail & Related papers  (2023-09-08T02:44:37Z)
• Tangent Bundle Convolutional Learning: from Manifolds to Cellular Sheaves and Back [84.61160272624262]
  We define tangent bundle filters and tangent bundle neural networks (TNNs) based on this convolution operation. Tangent bundle filters admit a spectral representation that generalizes the ones of scalar manifold filters, graph filters and standard convolutional filters in continuous time. We numerically evaluate the effectiveness of the proposed architecture on various learning tasks.
  arXiv  Detail & Related papers  (2023-03-20T17:57:15Z)
• A Unified Algebraic Perspective on Lipschitz Neural Networks [88.14073994459586]
  This paper introduces a novel perspective unifying various types of 1-Lipschitz neural networks. We show that many existing techniques can be derived and generalized via finding analytical solutions of a common semidefinite programming (SDP) condition. Our approach, called SDP-based Lipschitz Layers (SLL), allows us to design non-trivial yet efficient generalization of convex potential layers.
  arXiv  Detail & Related papers  (2023-03-06T14:31:09Z)
• Tangent Bundle Filters and Neural Networks: from Manifolds to Cellular Sheaves and Back [114.01902073621577]
  We use the convolution to define tangent bundle filters and tangent bundle neural networks (TNNs) We discretize TNNs both in space and time domains, showing that their discrete counterpart is a principled variant of the recently introduced Sheaf Neural Networks. We numerically evaluate the effectiveness of the proposed architecture on a denoising task of a tangent vector field over the unit 2-sphere.
  arXiv  Detail & Related papers  (2022-10-26T21:55:45Z)
• Differentiating through the Fr\'echet Mean [51.32291896926807]
  Fr'echet mean is a generalization of the Euclidean mean. We show how to differentiate through the Fr'echet mean for arbitrary Riemannian manifold. This fully integrates the Fr'echet mean into the hyperbolic neural network pipeline.
  arXiv  Detail & Related papers  (2020-02-29T19:49:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.