Understanding Generalization through Visualizations

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 u...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Huang, W Ronny, Emam, Zeyad, Goldblum, Micah, Fowl, Liam, Terry, J K, Huang, Furong, Goldstein, Tom
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 15.11.2020
Subjects
Neural networks
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422