Metraipolis › archive › dc_b479c2aa30c8
A Parametric Linear Conic Projection for Structured Sparse Attention — arXiv:2611.04479
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04479
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T18:34:39.394Z
- SHA-256 of the archived text
e6452c696230aa3e10c5dbca82e520225b0be2517581d245196e59810ef2274e- Stable URL of this page
https://metraipolis.com/documento/dc_b479c2aa30c8
How to cite
A Parametric Linear Conic Projection for Structured Sparse Attention — arXiv:2611.04479 — arXiv (en), https://arxiv.org/abs/2611.04479 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b479c2aa30c8 (Metraipolis archive dc_b479c2aa30c8, sha256 e6452c696230aa3e10c5dbca82e520225b0be2517581d245196e59810ef2274e)
BibTeX
@misc{dcb479c2aa30c8,
title = {A Parametric Linear Conic Projection for Structured Sparse Attention — arXiv:2611.04479},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04479},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b479c2aa30c8; sha256 e6452c696230aa3e10c5dbca82e520225b0be2517581d245196e59810ef2274e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04479. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In this paper, we introduce the Cone Alignment Index (CAI), a scale-invariant sparsity measure associated with a Lorentz-cone geometry. We provide a probabilistic analysis of the distribution of the CAI score, including a general theorem and explicit corollaries for Gaussian and uniform distributions. As a consequence, we show that, in the high-sparsity regime, the probability that the samples lie within the convex cone tends to one. Building upon this formulation, we derive two complementary projections: the \emph{Parametric Linear Conic Projection} (PLCP), an efficient closed-form approximation, and the \emph{Parametric Euclidean Conic Projection} (PECP), the exact Euclidean projection onto the cone boundary. Our analysis establishes several fundamental theoretical properties. We prove that PLCP and PECP are collinear, differ only by a positive radial scaling factor, and induce exactly the same sparsity threshold, thereby preserving an identical active support. Furthermore, we derive a support-identification theorem showing that, for any prescribed sparsity level $l<n$, the number of coefficients discarded at each iteration is theoretically controlled. Building on this theoretical foundation, we develop a bilevel PLCP framework for structured matrix sparsification. The proposed method naturally generates hardware-friendly structured sparsity patterns, including row-wise, column-wise, and diagonal masks, making it particularly well suited for accelerating Transformer attention mechanisms.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04479 — 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 2026-11-04T18:32:37.309Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).