不训练直接找最小网络，随机探索+逐步剪枝，效率更高
Random Cloud: Finding Minimal Neural Architectures Without Training
- 随机初始化网络，无反向传播地探索结构，逐步删减冗余连接
- 7个数据集上6次超越基线，Sonar上准确率提升4.9个百分点，参数降87%
- 比传统剪枝快0.67~0.94倍，避免训练完整网络
我提出一种名为「Random Cloud」的训练无关神经架构搜索方法，通过随机探索与渐进式结构简化，发现前馈网络的最小拓扑结构。不同于需经历训练-剪枝-再训练循环的后训练剪枝方法，该方法在无需反向传播的前提下评估随机初始化网络，逐步缩减其结构，仅对最优最小候选进行最终训练。我在7个分类基准上与幅度剪枝和随机剪枝基线对比，结果表明，在6个数据集上表现相当或更优，尤其在Sonar数据集上相较幅度剪枝实现+4.9个百分点的显著准确率提升（p=0.017），同时减少87%参数量。关键的是，在5个数据集中的4个上，该方法比两种剪枝基线更快（成本仅为完整训练的0.67–0.94倍），因完全避免了对全尺寸网络的训练。
原文摘要 · Abstract (English)
I propose the \emph{Random Cloud} method, a training-free approach to neural architecture search that discovers minimal feedforward network topologies through stochastic exploration and progressive structural reduction. Unlike post-training pruning methods that require a full train-prune-retrain cycle, this method evaluates randomly initialized networks without backpropagation, progressively reduces their topology, and only trains the best minimal candidate at the end. I evaluate on 7 classification benchmarks against magnitude pruning and random pruning baselines. The Random Cloud matches or outperforms both baselines in 6 of 7 datasets, achieving statistically significant improvements on Sonar ($+4.9$pp accuracy, $p{=}0.017$ vs magnitude pruning) with 87\% parameter reduction. Crucially, the method is faster than both pruning baselines in 4 of 5 datasets (0.67--0.94$\times$ the cost of full training), since it avoids training the full-size network entirely.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。