DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splitting

Analyzing the worst-case performance of deep neural networks against input perturbations amounts to solving a large-scale non-convex optimization problem, for which several past works have proposed convex relaxations as a promising alternative. However, even for reasonably-sized neural networks, the...

全面介紹

書目詳細資料

發表在:	IEEE Open Journal of Control Systems
Main Authors:	Shaoru Chen, Eric Wong, J. Zico Kolter, Mahyar Fazlyab
格式:	Article
語言:	英语
出版:	IEEE 2022-01-01
主題:	ADMM neural network verification operator splitting
在線閱讀:	https://ieeexplore.ieee.org/document/9811356/