arXiv：cs.LG· Yilang Zhang, Bingcong Li, Niao He, Georgios B. Giannakis·· 5 小时前AI 评分40
ANCRe：面向高效深度扩展的自适应神经连接重分配
ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling
AI 导读
研究者提出 ANCRe，一种轻量框架，通过参数化并从数据中学习残差连接布局，实现残差连接的自适应重分配，计算与内存开销低于 1%。理论分析证明残差连接布局会从根本上影响收敛行为，甚至带来收敛速率的指数级差距。在大语言模型预训练、扩散模型和深层 ResNet 上的实验显示，ANCRe 相比传统残差连接持续加速收敛、提升性能并增强深度效率。
正文
Abstract:Scaling network depth has been a central driver behind the success of modern foundation models, yet recent investigations suggest that deep layers are often underutilized. This paper revisits the default mechanism for deepening neural networks, namely residual connections, from an optimization perspective. Rigorous analysis proves that the layout of residual connections can fundamentally shape convergence behavior, and even induces an exponential gap in convergence rates. Prompted by this insight, we introduce adaptive neural connection reassignment (ANCRe), a principled and lightweight framework that parameterizes and learns residual connectivities from the data. ANCRe adaptively reassigns residual connections with negligible computational and memory overhead ($<1\%$), while enabling more effective utilization of network depth. Extensive numerical tests across pre-training of large language models, diffusion models, and deep ResNets demonstrate consistently accelerated convergence, boosted performance, and enhanced depth efficiency over conventional residual connections.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2602.09009 [cs.LG] |
| (or arXiv:2602.09009v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2602.09009 arXiv-issued DOI via DataCite |
Submission history
From: Yilang Zhang [view email]
[v1]
Mon, 9 Feb 2026 18:54:18 UTC (5,679 KB)
[v2]
Thu, 1 Oct 2026 21:55:31 UTC (5,686 KB)
来源：arXiv：cs.LG · arxiv.org