Analytical bounds on the local Lipschitz constants of affine-ReLU functions
arXiv:2008.06141
Abstract
In this paper, we determine analytical bounds on the local Lipschitz constants of of affine functions composed with rectified linear units (ReLUs). Affine-ReLU functions represent a widely used layer in deep neural networks, due to the fact that convolution, fully-connected, and normalization functions are all affine, and are often followed by a ReLU activation function. Using an analytical approach, we mathematically determine upper bounds on the local Lipschitz constant of an affine-ReLU function, show how these bounds can be combined to determine a bound on an entire network, and discuss how the bounds can be efficiently computed, even for larger layers and networks. We show several examples by applying our results to AlexNet, as well as several smaller networks based on the MNIST and CIFAR-10 datasets. The results show that our method produces tighter bounds than the standard conservative bound (i.e. the product of the spectral norms of the layers' linear matrices), especially for small perturbations.
arXiv comment14 pages, 5 figures
References in corpus (7)
- Explaining and Harnessing Adversarial Examples
- Intriguing properties of neural networks
- One weird trick for parallelizing convolutional neural networks
- Robust Large Margin Deep Neural Networks
- Lipschitz constant estimation of Neural Networks via sparse polynomial optimization
- Exactly Computing the Local Lipschitz Constant of ReLU Networks
- Adversarial Lipschitz Regularization