arXiv (Cornell University) · 2019 · 53 citations · 20 references
ComputingComputer ScienceComputer SecurityMachine LearningVulnerability AnalysisDeep LearningNetwork RobustnessOptimization For Machine LearningOverfittingAdversarial RobustnessMean Field AnalysisMean-field TheoryNormalizationTraining Error ReductionWeight Decay
Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks. In many cases it indeed decreases the number of parameter updates required to achieve low training error. However, it also reduces robustness to small adversarial input perturbations and noise by double-digit percentages, as we show on five standard datasets. Furthermore, substituting weight decay for batch norm is sufficient to nullify the relationship between adversarial vulnerability and the input dimension. Our work is consistent with a mean-field analysis that found that batch norm causes exploding gradients.
20
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2015 · 18.8K citations
Estimation of Entropy and Mutual Information
Liam Paninski · Neural Computation · 2003 · 1.5K citations