arXiv：cs.LG· Rahul Goswami, Aryan Bhambu, Bittu Karmakar·· 3 小时前
LAIR-Net：面向表格回归的泄漏对齐脉冲残差网络
LAIR-Net: Leaky Alignment-Impulse Residual Networks for Tabular Regression
AI 导读
研究提出 LAIR-Net（Leaky Alignment-Impulse Residual Network），通过带泄漏的残差转换将浅层可学习锚点混入每个隐藏状态，改变深度随机模型仅靠堆叠随机变换扩展深度的做法。
正文
Abstract:Deep randomized models fix hidden-layer parameters through random initialization and learn only closed-form readouts, typically adding depth by stacking random trans formations without target-aware control of hidden-state evolution. We propose LAIR Net, the Leaky Alignment-Impulse Residual Network, which mixes a shallow learned anchor into each hidden state through a leaky residual transition. We derive a depth uniform bound on input-perturbation sensitivity and use controlled simulations to attribute gains over a randomized baseline to the anchor rather than recursion or added capacity. Benefits emerge when a nonlinear target structure is learnable at the available noise level and diminish for nearly linear targets or dominant noise. Across 23 benchmark datasets, LAIR-Net achieves the best average rank among eight randomized networks and twelve conventional models, with relative performance associated with the same nonlinear-structure and noise quantities identified in simulation.
| Subjects: | Machine Learning (stat.ML); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.11538 [stat.ML] |
| (or arXiv:2610.11538v1 [stat.ML] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11538 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rahul Goswami [view email]
[v1]
Thu, 8 Oct 2026 09:08:45 UTC (555 KB)
来源：arXiv：cs.LG · arxiv.org