arXiv：cs.LG· Santiago Florido Gomez, St\'ephane Rivaud·· 2 天前AI 评分32
CAGE-NAS：面向高效模型增长的可认证函数下降
CAGE-NAS: Certified Functional Descent for Efficient Model Growth
AI 导读
CAGE-NAS 提出在函数空间中以函数梯度的可容许性准则决定神经网络何时停止增长、何时扩展：只要当前表示能完成可认证的函数梯度下降步骤，架构就保持不变，准则失效时则进行保函数扩展并重新评估。
正文
Abstract:The progressive growth of neural networks requires deciding when the current representation remains sufficient for optimization and when it should be expanded. CAGE-NAS formulates this decision in function space through an admissibility criterion on approximations of the functional gradient. As long as a representation enables a certified Functional Gradient Descent step, the architecture remains fixed; when the criterion fails, a function-preserving expansion is applied and the resulting representation is evaluated again. As the main instance, we study the family induced by the tangent space, using a regularized projection of the functional gradient. In a controlled setting with exact certification, CAGE-NAS produces architectures positioned above the 99.8th performance percentile by held-out RMSE among all admissible alternatives within the same parameter budget, without enumerating them during the growth trajectory.
| Comments: | 18 pages, 4 figures, 4 tables. Accepted at AXIOM 2026: Foundations of Efficient Deep Learning (NeurIPS 2026 Workshop) |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.01173 [cs.LG] |
| (or arXiv:2610.01173v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01173 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Santiago Florido [view email]
[v1]
Thu, 1 Oct 2026 06:46:47 UTC (1,748 KB)
来源：arXiv：cs.LG · arxiv.org