Metraipolis › archive › dc_289aed971a96
Beyond Quadratic Attention: Separable Gaussian Operators for ODE Vision Transformers — arXiv:2611.08236
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08236
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:50:54.734Z
- SHA-256 of the archived text
d40456de9acb452ec7509aea79c3d3833e4d98ceb5752d05bbfc9032306dbb5e- Stable URL of this page
https://metraipolis.com/documento/dc_289aed971a96
How to cite
Beyond Quadratic Attention: Separable Gaussian Operators for ODE Vision Transformers — arXiv:2611.08236 — arXiv (en), https://arxiv.org/abs/2611.08236 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_289aed971a96 (Metraipolis archive dc_289aed971a96, sha256 d40456de9acb452ec7509aea79c3d3833e4d98ceb5752d05bbfc9032306dbb5e)
BibTeX
@misc{dc289aed971a96,
title = {Beyond Quadratic Attention: Separable Gaussian Operators for ODE Vision Transformers — arXiv:2611.08236},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08236},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_289aed971a96; sha256 d40456de9acb452ec7509aea79c3d3833e4d98ceb5752d05bbfc9032306dbb5e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08236. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Self-attention carries a quadratic cost in token count, which limits how far Vision Transformers can scale with input resolution. We introduce SSoG, a separable sum-of-Gaussians spatial operator that replaces dense self-attention with a learned mixture of axis-factorized Gaussian kernels, reducing the per-layer cost from $\mathcal{O}(N^2)$ to subquadratic in $N$. Unlike dot-product self-attention, whose Lipschitz constant is unbounded outside a compact input domain, SSoG with fixed kernels is globally Lipschitz continuous, which, via the Picard--Lindelöf theorem, guarantees that the continuous-depth variant has a unique solution on the whole integration interval, a global guarantee that dense-attention counterparts lack in general. On CIFAR-100 at $224\times224$, in a matched discrete-Transformer setting and in the continuous setting, SSoG improves Top-1 accuracy by 2.2--4.1 points across three model widths while using 8.8--16.6\% fewer parameters, with depth and training recipe held fixed. In a looped-Transformer setting, SSoG improves Top-1 accuracy by 5.4--8.1 points. We further probe inference-time scaling by evaluating on inputs up to $1024\times1024$ at matched batch size: in the continuous-depth (Neural ODE) architecture, SSoG reaches up to 154\% higher throughput and over 60\% lower peak memory than dense attention, with the gap widening as resolution grows, consistent with the difference in asymptotic cost. In the discrete and looped settings, SSoG also achieves over 30\% higher throughput than dense attention at this resolution. Together, these results establish SSoG as a practical, parameter-efficient, and theoretically grounded alternative to dense attention across discrete, weight-shared, and continuous-depth Transformer variants.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.08236 — 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 2026-11-06T14:21:42.644Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).