English

PHEW: Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data

Machine Learning 2021-06-24 v2

Abstract

Methods that sparsify a network at initialization are important in practice because they greatly improve the efficiency of both learning and inference. Our work is based on a recently proposed decomposition of the Neural Tangent Kernel (NTK) that has decoupled the dynamics of the training process into a data-dependent component and an architecture-dependent kernel - the latter referred to as Path Kernel. That work has shown how to design sparse neural networks for faster convergence, without any training data, using the Synflow-L2 algorithm. We first show that even though Synflow-L2 is optimal in terms of convergence, for a given network density, it results in sub-networks with "bottleneck" (narrow) layers - leading to poor performance as compared to other data-agnostic methods that use the same number of parameters. Then we propose a new method to construct sparse networks, without any training data, referred to as Paths with Higher-Edge Weights (PHEW). PHEW is a probabilistic network formation method based on biased random walks that only depends on the initial weights. It has similar path kernel properties as Synflow-L2 but it generates much wider layers, resulting in better generalization and performance. PHEW achieves significant improvements over the data-independent SynFlow and SynFlow-L2 methods at a wide range of network densities.

Keywords

Cite

@article{arxiv.2010.11354,
  title  = {PHEW: Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data},
  author = {Shreyas Malakarjun Patil and Constantine Dovrolis},
  journal= {arXiv preprint arXiv:2010.11354},
  year   = {2021}
}

Comments

19 pages, 13 figures, 1 table, International COnference on Machine Learning 2021

R2 v1 2026-06-23T19:32:18.204Z