Metraipolis › archive › dc_7d3cb3d9f4e8
Linear Reusable Neural Bases Architecture for Network Compression — arXiv:2609.01550
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01550
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:34:26.124Z
- SHA-256 of the archived text
030403fce7dd117c7a08407b52ee4f7019be3d12f5ac8e122cb29a35b4b89668- Stable URL of this page
https://metraipolis.com/documento/dc_7d3cb3d9f4e8
How to cite
Linear Reusable Neural Bases Architecture for Network Compression — arXiv:2609.01550 — arXiv (en), https://arxiv.org/abs/2609.01550 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7d3cb3d9f4e8 (Metraipolis archive dc_7d3cb3d9f4e8, sha256 030403fce7dd117c7a08407b52ee4f7019be3d12f5ac8e122cb29a35b4b89668)
BibTeX
@misc{dc7d3cb3d9f4e8,
title = {Linear Reusable Neural Bases Architecture for Network Compression — arXiv:2609.01550},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01550},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7d3cb3d9f4e8; sha256 030403fce7dd117c7a08407b52ee4f7019be3d12f5ac8e122cb29a35b4b89668},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01550. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Memory constraints remain a critical bottleneck in the deployment of large-scale AI models. Parameter sharing across network depth reduces model storage, but repeatedly applying an identical transformation limits flexibility across layers. Inspired by time--memory trade-offs in classical algorithms, we introduce the Linear Reusable Neural Bases (LRNB) architecture, an RNN-based framework that improves parameter efficiency through parameter reuse at the \textit{neuron level}. Each feedforward residual module is represented as a linear combination of shared neural bases, with depth-specific learnable coefficients and optional shifts providing flexibility across layers. This formulation reduces parameter redundancy across depth and enables the construction of wider and deeper networks within a fixed parameter budget. We further provide a geometric interpretation of the neural bases from a vector-field perspective and extend the framework to linear projection modules. Experiments demonstrate that the LRNB architecture achieves comparable or lower final training loss than independently parameterized baselines while using fewer parameters and maintaining stable training dynamics. These findings support neuron-level reuse as a practical approach to parameter-efficient network design.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.01550 — 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 2026-10-17T06:15:12.910Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).