Random Search as a Baseline for Sparse Neural Network Architecture Search

arXiv:2403.08265v1 Announce Type: new
Abstract: Sparse neural networks have shown similar or better generalization performance than their dense counterparts while having higher parameter efficiency. This has motivated a number of works to learn, induce, or search for high performing sparse networks. While reports of quality or efficiency gains are impressive, standard baselines are lacking, therefore hindering having reliable comparability and reproducibility across methods. In this work, we provide an evaluation approach and a naive Random Search baseline method for finding …

abstract architecture arxiv cs.ai cs.lg cs.ne efficiency learn network network architecture networks neural network neural networks performance quality random reports search type