arXiv：cs.LG（机器学习，全量分类）· Jama Hussein Mohamud, Mirco Ravanelli·· 1 天前AI 评分38
随机递归模型 RRM：用层采样实现参数高效推理
Random Recursive Models
AI 导读
研究者提出随机递归模型（RRM），维护一个含 L 个已学习层的层池，对每个样本和每个递归步骤独立有放回地采样一层，共执行 T 步递归，从而在保持递归参数效率的同时实现灵活的层复用。
正文
Abstract:Recursive models create computational depth through parameter reuse, offering a parameter-efficient alternative to increasing model size. However, most recursive models repeatedly apply one learned transformation or a prescribed sequence of transformations, restricting computation to a fixed layer order. We introduce the Random Recursive Model (RRM), which maintains a pool of $L$ learned layers and performs $T$ recursive steps by sampling one layer independently with replacement for each example and step. This enables flexible layer reuse while retaining the parameter efficiency of recurrence. We evaluate RRM on challenging reasoning tasks, where it matches or exceeds the baselines, often with 50-75 % fewer parameters. RRM can vary its depth at inference, including beyond that seen during training, without retraining or adding parameters, improving tasks that benefit from deeper iterative computation. RRM also supports Monte Carlo inference and probabilistic test-time scaling, both of which improve performance without retraining. These insights may open new directions in neural network architecture design.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.00541 [cs.LG] |
| (or arXiv:2610.00541v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00541 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jama Hussein Mohamud [view email]
[v1]
Wed, 30 Sep 2026 18:23:14 UTC (302 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org