We investigate the difficulties of training sparse neural networks and make new observations about optimization dynamics and the energy landscape within the sparse regime. Recent work of \citep{Gale2019, Liu2018} has shown that sparse ResNet-50 architectures trained on ImageNet-2012 dataset converge to solutions that are significantly worse than those found by pruning. We show that, despite the failure of optimizers, there is a linear path with a monotonically decreasing objective from the initialization to the "good" solution. Additionally, our attempts to find a decreasing objective path from "bad" solutions to the "good" ones in the sparse subspace fail. However, if we allow the path to traverse the dense subspace, then we consistently find a path between two solutions. These findings suggest traversing extra dimensions may be needed to escape stationary points found in the sparse subspace.
@article{arxiv.1906.10732,
title = {The Difficulty of Training Sparse Neural Networks},
author = {Utku Evci and Fabian Pedregosa and Aidan Gomez and Erich Elsen},
journal= {arXiv preprint arXiv:1906.10732},
year = {2020}
}
Comments
sparse networks, pruning, energy landscape, sparsity