English

Finding trainable sparse networks through Neural Tangent Transfer

Machine Learning 2020-07-27 v2 Neural and Evolutionary Computing Machine Learning

Abstract

Deep neural networks have dramatically transformed machine learning, but their memory and energy demands are substantial. The requirements of real biological neural networks are rather modest in comparison, and one feature that might underlie this austerity is their sparse connectivity. In deep learning, trainable sparse networks that perform well on a specific task are usually constructed using label-dependent pruning criteria. In this article, we introduce Neural Tangent Transfer, a method that instead finds trainable sparse networks in a label-free manner. Specifically, we find sparse networks whose training dynamics, as characterized by the neural tangent kernel, mimic those of dense networks in function space. Finally, we evaluate our label-agnostic approach on several standard classification tasks and show that the resulting sparse networks achieve higher classification performance while converging faster.

Keywords

Cite

@article{arxiv.2006.08228,
  title  = {Finding trainable sparse networks through Neural Tangent Transfer},
  author = {Tianlin Liu and Friedemann Zenke},
  journal= {arXiv preprint arXiv:2006.08228},
  year   = {2020}
}

Comments

Accepted by ICML 2020

R2 v1 2026-06-23T16:19:39.208Z