Input Convex Lipschitz RNN: A Fast and Robust Approach for Engineering Tasks

arXiv:2401.07494v3 Announce Type: replace
Abstract: Computational efficiency and non-adversarial robustness are critical factors in real-world engineering applications. Yet, conventional neural networks often fall short in addressing both simultaneously, or even separately. Drawing insights from natural physical systems and existing literature, it is known that an input convex architecture enhances computational efficiency, while a Lipschitz-constrained architecture bolsters non-adversarial robustness. By leveraging the strengths of convexity and Lipschitz continuity, we develop a novel network architecture, termed Input Convex Lipschitz Recurrent Neural Networks. …

abstract adversarial applications architecture arxiv computational cs.ce cs.lg cs.sy eess.sy efficiency engineering insights literature natural networks neural networks rnn robust robustness systems tasks type world