A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks

Author name not available (Why is that?)

Publication date: 26 January 2023

Abstract: Counterexample-guided repair aims at creating neural networks with mathematical safety guarantees, facilitating the application of neural networks in safety-critical domains. However, whether counterexample-guided repair is guaranteed to terminate remains an open question. We approach this question by showing that counterexample-guided repair can be viewed as a robust optimisation algorithm. While termination guarantees for neural network repair itself remain beyond our reach, we prove termination for more restrained machine learning models and disprove termination in a general setting. We empirically study the practical implications of our theoretical results, demonstrating the suitability of common verifiers and falsifiers for repair despite a disadvantageous theoretical result. Additionally, we use our theoretical insights to devise a novel algorithm for repairing linear regression models based on quadratic programming, surpassing existing approaches.

Has companion code repository: https://github.com/sen-uni-kn/specrepair

This page was built for publication: A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6424511)