Efficient and sparse neural networks by pruning weights in a multiobjective learning approach

DOI10.1016/j.cor.2021.105676OpenAlexW3082139599WikidataQ111522174 ScholiaQ111522174MaRDI QIDQ2669736

Malena Reiners, Fabian Heldmann, Michael Stiglmayr, Kathrin Klamroth

Publication date: 9 March 2022

Published in: Computers \& Operations Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2008.13590

zbMATH Keywords

automated machine learning\(l_1\)-regularizationmultiobjective learningstochastic multi-gradient descentunstructured pruning

Mathematics Subject Classification ID

Operations research and management science (90Bxx)

Related Items (4)

Adaptive sampling stochastic multigradient algorithm for stochastic multiobjective optimization ⋮ PINN training using biobjective optimization: the trade-off between data loss and residual loss ⋮ Optimal deep neural networks by maximization of the approximation power ⋮ Accuracy and fairness trade-offs in machine learning: a stochastic multi-objective approach

Uses Software

• NBI
• MNIST
• Keras
• CIFAR
• RMSprop
• Adam
• BinaryNet
• PruneTrain

Cites Work

• Unnamed Item
• Unnamed Item
• Stochastic approach versus multiobjective approach for obtaining efficient solutions in stochastic multiobjective programming problems
• Steepest descent methods for multicriteria optimization.
• A stochastic multiple gradient descent algorithm
• Improving generalization of MLPs with multi-objective optimization
• Multi-objective machine learning
• Bicriteria Transportation Problem
• Optimization Methods for Large-Scale Machine Learning
• Multicriteria Optimization
• Asymptotic Distribution of Stochastic Approximation Procedures
• A Stochastic Approximation Method

This page was built for publication: Efficient and sparse neural networks by pruning weights in a multiobjective learning approach