Optimization of sparsity-constrained neural networks as a mixed integer linear program

DOI10.1007/s10957-023-02317-xOpenAlexW4387933920MaRDI QIDQ6145048

Bodo Rosenhahn

Publication date: 8 January 2024

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10957-023-02317-x

zbMATH Keywords

neural networksmixed integer linear programmingfeature selectionsparse networksresource optimization

Mathematics Subject Classification ID

Mixed integer programming (90C11) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Feature extraction. Foundations and applications. Papers from NIPS 2003 workshop on feature extraction, Whistler, BC, Canada, December 11--13, 2003. With CD-ROM.
• Logic and integer programming
• Deep neural networks and mixed integer linear optimization
• Optimization problems for machine learning: a survey
• Lossless compression of deep neural networks
• Between steps: intermediate relaxations between big-M and convex hull formulations
• Mathematical Programming in Neural Networks
• 10.1162/153244303322753616
• JANOS: An Integrated Predictive and Prescriptive Modeling Framework
• A logical calculus of the ideas immanent in nervous activity
• Strong mixed-integer programming formulations for trained neural networks
• Principled deep neural network training through linear programming

This page was built for publication: Optimization of sparsity-constrained neural networks as a mixed integer linear program