Robust Learning with Jacobian Regularization
arXiv:1908.02729
The paper proposes an efficient Jacobian regularization method for neural networks that enlarges classification margins and improves robustness to both random and adversarial input perturbations while maintaining good generalization.
Abstract
Design of reliable systems must guarantee stability against input perturbations. In machine learning, such guarantee entails preventing overfitting and ensuring robustness of models against corruption of input data. In order to maximize stability, we analyze and develop a computationally efficient implementation of Jacobian regularization that increases classification margins of neural networks. The stabilizing effect of the Jacobian regularizer leads to significant improvements in robustness, as measured against both random and adversarial input perturbations, without severely degrading generalization properties on clean data.
21 pages, 10 figures