Metraipolis › archive › dc_d439c8f6acb6
Minkowski Attractor Networks: Closed-Form Hyperbolic Flows for Visual Representations — arXiv:2609.37817
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37817
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:41:32.049Z
- SHA-256 of the archived text
67fa142d833a7f86990075bfda3e91dba9bcfb908ffd227c33c18327654809b0- Stable URL of this page
https://metraipolis.com/documento/dc_d439c8f6acb6
How to cite
Minkowski Attractor Networks: Closed-Form Hyperbolic Flows for Visual Representations — arXiv:2609.37817 — arXiv (en), https://arxiv.org/abs/2609.37817 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d439c8f6acb6 (Metraipolis archive dc_d439c8f6acb6, sha256 67fa142d833a7f86990075bfda3e91dba9bcfb908ffd227c33c18327654809b0)
BibTeX
@misc{dcd439c8f6acb6,
title = {Minkowski Attractor Networks: Closed-Form Hyperbolic Flows for Visual Representations — arXiv:2609.37817},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37817},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d439c8f6acb6; sha256 67fa142d833a7f86990075bfda3e91dba9bcfb908ffd227c33c18327654809b0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37817. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Geometric representation learning predominantly scaffolds representations onto flat Euclidean subspaces or compact product tori ($\mathbb{T}^K$). However, flat manifolds possess vanishing curvature and polynomial volume growth, inherently suffering from metric distortion when embedding multi-scale, tree-like visual hierarchies. While hyperbolic spaces ($\mathbb{H}^m$) circumvent this via constant negative curvature ($K<0$) and exponential volume expansion, prior hyperbolic deep architectures are hindered by computationally cumbersome Riemannian optimization, non-linear gyrovector calculus, and floating-point instabilities. In this work, we introduce \textbf{Minkowski Attractor Networks (MAN)}, an operator-splitting-inspired framework that embeds representations within pseudo-Riemannian Minkowski spacetime ($\mathbb{R}^{1,m}$). By framing hyperbolic manifolds as quadric level sets, MAN resolves hyperbolic geometry by combining linear Lorentz group transport with non-linear cone lifting and closed-form radial rescaling, evaluating in a single forward pass without numerical ODE solvers or iterative retractions. We establish \textbf{MAN-2D} ($\mathbb{R}^{1,1} \to \mathbb{H}^1$) as our primary, high-throughput visual backbone, which maximizes channel factorization granularity into $D/2$ independent two-dimensional Minkowski blocks. We further formulate \textbf{MAN-4D} ($\mathbb{R}^{1,3} \to \mathbb{H}^3$) as a spacetime extension, leveraging a commuting Cartan-subalgebra parameterization of $\mathrm{SO}^+(1,3)$ to evaluate 4D Lorentz isometries via two commuting 2D planar maps without matrix-exponential overhead.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.37817 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T18:04:24.912Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).