Understanding Generalization Through Visualizations
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
Text
Huang et al. "Understanding Generalization Through Visualizations." NeurIPS 2020 Workshops: ICBINB, 2020.Markdown
[Huang et al. "Understanding Generalization Through Visualizations." NeurIPS 2020 Workshops: ICBINB, 2020.](https://mlanthology.org/neuripsw/2020/huang2020neuripsw-understanding/)BibTeX
@inproceedings{huang2020neuripsw-understanding,
title = {{Understanding Generalization Through Visualizations}},
author = {Huang, W Ronny and Emam, Zeyad and Goldblum, Micah and Fowl, Liam H and Terry, J K and Huang, Furong and Goldstein, Tom},
booktitle = {NeurIPS 2020 Workshops: ICBINB},
year = {2020},
url = {https://mlanthology.org/neuripsw/2020/huang2020neuripsw-understanding/}
}