Structured pruning of neural networks for constraints learning

DOI10.1016/J.ORL.2024.107194MaRDI QIDQ6988271zbMATH OpenFDO

Authors Matteo Cacciola, Antonio Frangioni, Andrea Lodi

Publication date 5 May 2025

Published in Operations Research Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.ORL.2024.107194

zbMATH Keywords

artificial neural networksmixed integer programmingmodel compressionpruning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Mixed integer programming (90C11)

Cites work

• Approximated perspective relaxations: a project and lift approach
• Deep neural networks and mixed integer linear optimization
• Deep Neural Networks Pruning via the Structured Perspective Regularization
• Improving the approximated projected perspective reformulation by dual information
• JANOS: An Integrated Predictive and Prescriptive Modeling Framework
• Lossless compression of deep neural networks
• OAMIP: optimizing ANN architectures using mixed-integer programming
• Projected perspective reformulations with applications in design problems
• Strengthening the sequential convex MINLP technique by perspective reformulations
• Strong mixed-integer programming formulations for trained neural networks
• The adaptive BerHu penalty in robust regression

This page was built for publication: Structured pruning of neural networks for constraints learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6988271)