Tessellation Groups, Harmonic Analysis on Non-compact Symmetric Spaces and the Heat Kernel in view of Cartan Convolutional Neural Networks
Pietro Fr\'e, Federico Milanesio, Marcelo Oyarzo, Matteo Santoro, Mario Trigiante

TL;DR
This paper advances mathematical foundations for Cartan neural networks by exploring harmonic analysis, group theory, and heat kernels on non-compact symmetric spaces, aiming to improve geometric deep learning models.
Contribution
It introduces new group theoretical constructions, tiling groups, and harmonic analysis techniques relevant for Cartan neural networks on non-compact symmetric spaces.
Findings
Constructed separators for all non-compact symmetric spaces U/H.
Derived a new representation of the Laplacian Green function and Heat Kernel on hyperbolic spaces.
Proposed a novel approach to construct Laplacian eigenfunctions on Riemann surfaces using Abel-Jacobi maps.
Abstract
In this paper, we continue the development of the Cartan neural networks programme, launched with three previous publications, by focusing on some mathematical foundational aspects that we deem necessary for our next steps forward. The mathematical and conceptual results are diverse and span various mathematical fields, but the inspiring motivation is unified. The aim is to introduce layers that are mathematically modeled as non-compact symmetric spaces, each mapped onto the next one by solvable group homomorphisms. In particular, in the spirit of Convolutional neural networks, we have introduced the notion of Tits Satake (TS) vector bundles where the TS submanifold is the base space. Within this framework, the tiling of the base manifold, the representation of bundle sections using harmonics, and the need for a general theory of separator walls motivated a series of mathematical…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
