Understanding Adversarial Robustness Through Loss Landscape Geometries

The pursuit of explaining and improving generalization in deep learning has elicited efforts both in regularization techniques as well as visualization techniques of the loss surface geometry. The latter is related to the intuition prevalent in the community that flatter local optima leads to lower...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-07
Main Authors: Prabhu, Vinay Uday, Dian Ang Yap, Xu, Joyce, Whaley, John
Format: Article
Language:English
Subjects:
Data augmentation
Landscape
Machine learning
Regularization
Surface geometry
Training
Visualization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The pursuit of explaining and improving generalization in deep learning has elicited efforts both in regularization techniques as well as visualization techniques of the loss surface geometry. The latter is related to the intuition prevalent in the community that flatter local optima leads to lower generalization error. In this paper, we harness the state-of-the-art "filter normalization" technique of loss-surface visualization to qualitatively understand the consequences of using adversarial training data augmentation as the explicit regularization technique of choice. Much to our surprise, we discover that this oft deployed adversarial augmentation technique does not actually result in "flatter" loss-landscapes, which requires rethinking adversarial training generalization, and the relationship between generalization and loss landscapes geometries.
ISSN:2331-8422