Global optimization of objective functions represented by ReLU networks

DOI10.1007/s10994-021-06050-2arXiv2010.03258OpenAlexW3207272170MaRDI QIDQ6053800

Kyle D. Julian, Guy Katz, Clark Barrett, Christopher A. Strong, Mykel J. Kochenderfer, Haoze Wu, Aleksandar Zeljić

Publication date: 24 October 2023

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

Full work available at URL: https://arxiv.org/abs/2010.03258

zbMATH Keywords

optimizationadversarial examplesneural network verificationMarabou

Mathematics Subject Classification ID

Specification and verification (program logics, model checking, etc.) (68Q60) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Neural networks for control systems - a survey
• Deep neural networks and mixed integer linear optimization
• Safety verification of deep neural networks
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Verification of deep convolutional neural networks using ImageStars
• \textsc{OptiMathSAT}: a tool for optimization modulo theories
• Algorithm 778: L-BFGS-B
• Pushing the Envelope of Optimization Modulo Theories with Linear-Arithmetic Cost Functions

This page was built for publication: Global optimization of objective functions represented by ReLU networks