Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 15364-15376, 2019.
Lipschitz constraints under L-2 norm on deep neural networks are useful for provable adversarial robustness bounds, stable training, and Wasserstein distance estimation. While heuristic approaches such as the gradient penalty have seen much practical success, it is challenging to achieve similar practical performance while provably enforc...More
PPT (Upload PPT)