English

Estimating the Generalization in Deep Neural Networks via Sparsity

Computer Vision and Pattern Recognition 2023-11-21 v3

Abstract

Generalization is the key capability for deep neural networks (DNNs). However, it is challenging to give a reliable measure of the generalization ability of a DNN via only its nature. In this paper, we propose a novel method for estimating the generalization gap based on network sparsity. In our method, two key quantities are proposed first. They have close relationship with the generalization ability and can be calculated directly from the training results alone. Then a simple linear model involving two key quantities are constructed to give accurate estimation of the generalization gap. By training DNNs with a wide range of generalization gap on popular datasets, we show that our key quantities and linear model could be efficient tools for estimating the generalization gap of DNNs.

Keywords

Cite

@article{arxiv.2104.00851,
  title  = {Estimating the Generalization in Deep Neural Networks via Sparsity},
  author = {Yang Zhao and Hao Zhang},
  journal= {arXiv preprint arXiv:2104.00851},
  year   = {2023}
}
R2 v1 2026-06-24T00:47:42.710Z