Notes on Margin Training and Margin p-Values for Deep Neural Network Classifiers
arXiv:1910.08032
Abstract
We provide a new local class-purity theorem for Lipschitz continuous DNN classifiers. In addition, we discuss how to achieve classification margin for training samples. Finally, we describe how to compute margin p-values for test samples.
References in corpus (6)
- Provable defenses against adversarial examples via the convex outer adversarial polytope
- Robustness May Be at Odds with Accuracy
- Parseval Networks: Improving Robustness to Adversarial Examples
- Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks
- Towards Fast Computation of Certified Robustness for ReLU Networks
- Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks