Search Results for author:
Found 3 papers, 3 papers with code
1-Lipschitz Layers Compared: Memory, Speed, and Certifiable Robustness
The robustness of neural networks against input perturbations with bounded magnitude represents a serious concern in the deployment of deep learning models in safety-critical systems.
1-Lipschitz Neural Networks are more expressive with N-Activations
A crucial property for achieving secure, trustworthy and interpretable deep learning systems is their robustness: small changes to a system's inputs should not result in large changes to its outputs.
Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks
In this work, we propose a new technique for constructing such Lipschitz networks that has a number of desirable properties: it can be applied to any linear network layer (fully-connected or convolutional), it provides formal guarantees on the Lipschitz constant, it is easy to implement and efficient to run, and it can be combined with any training objective and optimization method.
