Convex Neural Network Synthesis for Robustness in the 1-Norm
Abstract
With neural networks being used to control safety-critical systems, they increasingly have to be both accurate (in the sense of matching inputs to outputs) and robust. However, these two properties are often at odds with each other and a trade-off has to be navigated. To address this issue, this paper proposes a method to generate an approximation of a neural network which is certifiably more robust. Crucially, the method is fully convex and posed as a semi-definite programme. An application to robustifying model predictive control is used to demonstrate the results. The aim of this work is to introduce a method to navigate the neural network robustness/accuracy trade-off.
Cite
Text
Drummond et al. "Convex Neural Network Synthesis for Robustness in the 1-Norm." Proceedings of the 6th Annual Learning for Dynamics & Control Conference, 2024.Markdown
[Drummond et al. "Convex Neural Network Synthesis for Robustness in the 1-Norm." Proceedings of the 6th Annual Learning for Dynamics & Control Conference, 2024.](https://mlanthology.org/l4dc/2024/drummond2024l4dc-convex/)BibTeX
@inproceedings{drummond2024l4dc-convex,
title = {{Convex Neural Network Synthesis for Robustness in the 1-Norm}},
author = {Drummond, Ross and Guiver, Chris and Turner, Matthew},
booktitle = {Proceedings of the 6th Annual Learning for Dynamics & Control Conference},
year = {2024},
pages = {1388-1399},
volume = {242},
url = {https://mlanthology.org/l4dc/2024/drummond2024l4dc-convex/}
}