A New Angle on L2 Regularization
arXiv:1806.11186
Abstract
Imagine two high-dimensional clusters and a hyperplane separating them. Consider in particular the angle between: the direction joining the two clusters' centroids and the normal to the hyperplane. In linear classification, this angle depends on the level of L2 regularization used. Can you explain why?
arXiv commentAn explorable explanation on the phenomenon of adversarial examples in linear classification and its relation to L2 regularization. Interactive version available at: https://thomas-tanay.github.io/post--L2-regularization/
References in corpus (13)
- Distilling the Knowledge in a Neural Network
- Ensemble Adversarial Training: Attacks and Defenses
- On Calibration of Modern Neural Networks
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Understanding deep learning requires rethinking generalization
- Synthesizing Robust Adversarial Examples
- Towards Deep Neural Network Architectures Robust to Adversarial Examples
- Robust Physical-World Attacks on Deep Learning Models
- Detecting Adversarial Samples from Artifacts
- On the (Statistical) Detection of Adversarial Examples
- Provably Minimally-Distorted Adversarial Examples
- Practical Black-Box Attacks against Machine Learning
- Suppressing the Unusual: towards Robust CNNs using Symmetric Activation Functions