Understanding Generalization through Visualizations
Machine Learning
2021-11-17 v6 Neural and Evolutionary Computing
Machine Learning
Abstract
The power of neural networks lies in their ability to generalize to unseen data, yet the underlying reasons for this phenomenon remain elusive. Numerous rigorous attempts have been made to explain generalization, but available bounds are still quite loose, and analysis does not always lead to true understanding. The goal of this work is to make generalization more intuitive. Using visualization methods, we discuss the mystery of generalization, the geometry of loss landscapes, and how the curse (or, rather, the blessing) of dimensionality causes optimizers to settle into minima that generalize well.
Cite
@article{arxiv.1906.03291,
title = {Understanding Generalization through Visualizations},
author = {W. Ronny Huang and Zeyad Emam and Micah Goldblum and Liam Fowl and J. K. Terry and Furong Huang and Tom Goldstein},
journal= {arXiv preprint arXiv:1906.03291},
year = {2021}
}
Comments
8 pages (excluding acknowledgments and references), 8 figures