Deep Neural Networks Pruning via the Structured Perspective Regularization

DOI10.1137/22m1542313zbMath1530.68226arXiv2206.14056OpenAlexW4389339766MaRDI QIDQ6148352

Antonio Frangioni, Matteo Cacciola, Unnamed Author, Andrea Lodi

Publication date: 11 January 2024

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2206.14056

zbMATH Keywords

optimizationartificial neural networkspruning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Convex programming (90C25) Applications of mathematical programming (90C90) Integer programming (90C10)

Cites Work

• Unnamed Item
• Approximated perspective relaxations: a project and lift approach
• Deep neural networks and mixed integer linear optimization
• Lossless compression of deep neural networks
• On mathematical programming with indicator constraints
• Perspective cuts for a class of convex 0-1 mixed integer programs
• The adaptive BerHu penalty in robust regression
• Projected Perspective Reformulations with Applications in Design Problems
• Fast Convex Pruning of Deep Neural Networks
• Sensitivity-Informed Provable Pruning of Neural Networks
• Regularization and Variable Selection Via the Elastic Net
• Robust Estimation of a Location Parameter
• Strong mixed-integer programming formulations for trained neural networks
• OAMIP: optimizing ANN architectures using mixed-integer programming