On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications
Year: 2021
Type: preprint
Abstract: This paper follows up on a recent work of Neu et al. (2021) and presents some new information-theoretic upper bounds for the generalization error of machine learning models, such as neural networks, trained with SGD. We apply these bounds to analyzing the generalization behaviour of linear and two-layer ReLU networks. Experimental study of these bounds provide some insights on the SGD training of neural networks. They also point to a new and simple regularization scheme which we show performs comparably to the current state of the art.
Source: arXiv (Cornell University)
Authors: Wang, Ziqiao, Mao, Yongyi
Institution: University of Ottawa
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3202669415