English
Related papers

Related papers: Consistent Geometric Deep Learning via Hilbert Bun…

200 papers

In this work we introduce a convolution operation over the tangent bundle of Riemann manifolds in terms of exponentials of the Connection Laplacian operator. We define tangent bundle filters and tangent bundle neural networks (TNNs) based…

Signal Processing · Electrical Eng. & Systems 2024-03-19 Claudio Battiloro , Zhiyang Wang , Hans Riess , Paolo Di Lorenzo , Alejandro Ribeiro

In this work we introduce a convolution operation over the tangent bundle of Riemannian manifolds exploiting the Connection Laplacian operator. We use the convolution to define tangent bundle filters and tangent bundle neural networks…

Signal Processing · Electrical Eng. & Systems 2022-11-21 Claudio Battiloro , Zhiyang Wang , Hans Riess , Paolo Di Lorenzo , Alejandro Ribeiro

CoVariance Neural Networks (VNNs) perform graph convolutions on the empirical covariance matrix of signals defined over finite-dimensional Hilbert spaces, motivated by robustness and transferability properties. Yet, little is known about…

Machine Learning · Computer Science 2025-09-18 Claudio Battiloro , Andrea Cavallo , Elvin Isufi

We propose Fiber Bundle Networks (FiberNet), a novel machine learning framework integrating differential geometry with machine learning. Unlike traditional deep neural networks relying on black-box function fitting, we reformulate…

Machine Learning · Computer Science 2025-12-02 Dong Liu

We study the discrete-to-continuum consistency of the training of shallow graph convolutional neural networks (GCNNs) on proximity graphs of sampled point clouds under a manifold assumption. Graph convolution is defined spectrally via the…

Machine Learning · Statistics 2026-01-12 Johanna Tengler , Christoph Brune , José A. Iglesias

Geometric Deep Learning (GDL) unifies a broad class of machine learning techniques from the perspectives of symmetries, offering a framework for introducing problem-specific inductive biases like Graph Neural Networks (GNNs). However, the…

Machine Learning · Computer Science 2024-08-29 Osvaldo Velarde , Lucas Parra , Paolo Boldi , Hernan Makse

The absence of intrinsic adjacency relations and orientation systems in hypergraphs creates fundamental challenges for constructing sheaf Laplacians of arbitrary degrees. We resolve these limitations through symmetric simplicial sets…

Machine Learning · Computer Science 2025-08-01 Seongjin Choi , Gahee Kim , Yong-Geun Oh

Recent research in the theory of overparametrized learning has sought to establish generalization guarantees in the interpolating regime. Such results have been established for a few common classes of methods, but so far not for ensemble…

Machine Learning · Statistics 2022-05-20 Yutong Wang , Clayton D. Scott

We survey the mathematical foundations of geometric deep learning, focusing on group equivariant and gauge equivariant neural networks. We develop gauge equivariant convolutional neural networks on arbitrary manifolds $\mathcal{M}$ using…

Non-Euclidean constraints are inherent in many kinds of data in computer vision and machine learning, typically as a result of specific invariance requirements that need to be respected during high-level inference. Often, these geometric…

Computer Vision and Pattern Recognition · Computer Science 2017-09-26 Suhas Lohit , Pavan Turaga

Matrix completion models are among the most common formulations of recommender systems. Recent works have showed a boost of performance of these techniques when introducing the pairwise relationships between users/items in the form of…

Machine Learning · Computer Science 2017-04-25 Federico Monti , Michael M. Bronstein , Xavier Bresson

We develop a Hilbert space framework for a number of general multi-scale problems from dynamics. The aim is to identify a spectral theory for a class of systems based on iterations of a non-invertible endomorphism. We are motivated by the…

Dynamical Systems · Mathematics 2007-05-23 Dorin Ervin Dutkay , Palle E. T. Jorgensen

In this work, we build a generic architecture of Convolutional Neural Networks to discover empirical properties of neural networks. Our first contribution is to introduce a state-of-the-art framework that depends upon few hyper parameters…

Computer Vision and Pattern Recognition · Computer Science 2017-03-07 Edouard Oyallon

We introduce two constructions in geometric deep learning for 1) transporting orientation-dependent convolutional filters over a manifold in a continuous way and thereby defining a convolution operator that naturally incorporates the…

Machine Learning · Computer Science 2021-06-02 Stefan Sommer , Alex Bronstein

Establishing accurate morphological measurements of galaxies in a reasonable amount of time for future big-data surveys such as EUCLID, the Large Synoptic Survey Telescope or the Wide Field Infrared Survey Telescope is a challenge. Because…

Instrumentation and Methods for Astrophysics · Physics 2017-06-14 D. Tuccillo , M. Huertas-Company , E. Decenciere , S. Velasco-Forero

Multimodal data provide complementary information of a natural phenomenon by integrating data from various domains with very different statistical properties. Capturing the intra-modality and cross-modality information of multimodal data is…

Machine Learning · Computer Science 2021-11-29 Maysam Behmanesh , Peyman Adibi , Mohammad Saeed Ehsani , Jocelyn Chanussot

This paper develops a novel mathematical framework for collaborative learning by means of geometrically inspired kernel machines which includes statements on the bounds of generalisation and approximation errors, and sample complexity. For…

Cellular sheaves equip graphs with a "geometrical" structure by assigning vector spaces and linear maps to nodes and edges. Graph Neural Networks (GNNs) implicitly assume a graph with a trivial underlying sheaf. This choice is reflected in…

Machine Learning · Computer Science 2023-01-09 Cristian Bodnar , Francesco Di Giovanni , Benjamin Paul Chamberlain , Pietro Liò , Michael M. Bronstein

We introduce the concept of Hypoelliptic Diffusion Maps (HDM), a framework generalizing Diffusion Maps in the context of manifold learning and dimensionality reduction. Standard non-linear dimensionality reduction methods (e.g., LLE,…

Statistics Theory · Mathematics 2015-03-19 Tingran Gao

Manifold learning approaches seek the intrinsic, low-dimensional data structure within a high-dimensional space. Mainstream manifold learning algorithms, such as Isomap, UMAP, $t$-SNE, Diffusion Map, and Laplacian Eigenmaps do not use data…

Machine Learning · Statistics 2023-07-04 Jake S. Rhodes
‹ Prev 1 2 3 10 Next ›