A minimax optimal control approach for robust neural ODEs

arXiv:2310.17584v3 Announce Type: replace-cross
Abstract: In this paper, we address the adversarial training of neural ODEs from a robust control perspective. This is an alternative to the classical training via empirical risk minimization, and it is widely used to enforce reliable outcomes for input perturbations. Neural ODEs allow the interpretation of deep neural networks as discretizations of control systems, unlocking powerful tools from control theory for the development and the understanding of machine learning. In this specific case, we formulate …

abstract adversarial adversarial training arxiv control cs.lg cs.sy eess.sy interpretation math.oc minimax paper perspective risk robust training type via