Random Cloud: Finding Minimal Neural Architectures Without Training

arXiv:2604.26830v1 Announce Type: cross Abstract: I propose the 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 (+4.9pp 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--0.94imes the cost of full training), since it avoids training the full-size network entirely.

Source: arXiv cs.AI | 2026-04-30