ModelGuard: Runtime Validation of Lipschitz-continuous Models

2021/04/30 by Carpenter, Taylor J., Ivanov, Radoslav, Lee, Insup +1 · 1 citation
#FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2104.15006

Abstract

This paper presents ModelGuard, a sampling-based approach to runtime model validation for Lipschitz-continuous models. Although techniques exist for the validation of many classes of models the majority of these methods cannot be applied to the whole of Lipschitz-continuous models, which includes neural network models. Additionally, existing techniques generally consider only white-box models. By taking a sampling-based approach, we can address black-box models, represented only by an input-output relationship and a Lipschitz constant. We show that by randomly sampling from a parameter space and evaluating the model, it is possible to guarantee the correctness of traces labeled consistent and provide a confidence on the correctness of traces labeled inconsistent. We evaluate the applicability and scalability of ModelGuard in three case studies, including a physical platform.

Cited by

• Towards Unified Probabilistic Verification and Validation of Vision-Based Autonomy

Related

• Lipschitz Continuity in Model-based Reinforcement Learning
• Data-Driven Model Invalidation for Unknown Lipschitz Continuous Systems via Abstraction
• Regularisation of Neural Networks by Enforcing Lipschitz Continuity
• Some Fundamental Aspects about Lipschitz Continuity of Neural Networks
• Lipschitz Continuity in Deep Learning: A Systematic Review of Theoretical Foundations, Estimation Methods, Regularization Approaches, and Certifiable Robustness