Speeding up neural network robustness verification via algorithm configuration and an optimised mixed integer linear programming solver portfolio

DOI10.1007/s10994-022-06212-wOpenAlexW4297691576WikidataQ114224929 ScholiaQ114224929MaRDI QIDQ6097125

Jan N. van Rijn, Holger H. Hoos, Matthias Koenig

Publication date: 12 June 2023

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-022-06212-w

zbMATH Keywords

mixed integer programmingalgorithm selectionneural network verificationautomated algorithm configuration

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• The configurable SAT solver challenge (CSSC)
• Deep neural networks and mixed integer linear optimization
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Automatically improving the anytime behaviour of optimisation algorithms
• ParamILS: An Automatic Algorithm Configuration Framework
• Algorithm Selection for Combinatorial Search Problems: A Survey
• Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks
• Random forests

This page was built for publication: Speeding up neural network robustness verification via algorithm configuration and an optimised mixed integer linear programming solver portfolio