Efficient and sparse neural networks by pruning weights in a multiobjective learning approach
From MaRDI portal
Publication:2669736
Recommendations
- Joint structure and parameter optimization of multiobjective sparse neural network
- Neural Network Pruning with Tukey-Kramer Multiple Comparison Procedure
- Fast convex pruning of deep neural networks
- Sensitivity-informed provable pruning of neural networks
- Make \(\ell_1\) regularization effective in training sparse CNN
Cites work
- scientific article; zbMATH DE number 1569102 (Why is no real title available?)
- A Stochastic Approximation Method
- A stochastic multiple gradient descent algorithm
- Asymptotic Distribution of Stochastic Approximation Procedures
- Bicriteria Transportation Problem
- Deep learning
- Improving generalization of MLPs with multi-objective optimization
- Multi-objective machine learning
- Multicriteria Optimization
- Optimization methods for large-scale machine learning
- Steepest descent methods for multicriteria optimization.
- Stochastic approach versus multiobjective approach for obtaining efficient solutions in stochastic multiobjective programming problems
Cited in
(14)- PINN training using biobjective optimization: the trade-off between data loss and residual loss
- Fast convex pruning of deep neural networks
- Deep Neural Networks Pruning via the Structured Perspective Regularization
- scientific article; zbMATH DE number 7626756 (Why is no real title available?)
- Efficient and Sparse Neural Networks by Pruning Weights in a Multiobjective Learning Approach
- Sensitivity-informed provable pruning of neural networks
- Joint structure and parameter optimization of multiobjective sparse neural network
- Adaptive sampling stochastic multigradient algorithm for stochastic multiobjective optimization
- Sparsity through evolutionary pruning prevents neuronal networks from overfitting
- Pruning during training by network efficacy modeling
- Optimal deep neural networks by maximization of the approximation power
- MW-OBS: An improved pruning method for topology design of neural networks
- Accuracy and fairness trade-offs in machine learning: a stochastic multi-objective approach
- Training thinner and deeper neural networks: jumpstart regularization
This page was built for publication: Efficient and sparse neural networks by pruning weights in a multiobjective learning approach
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2669736)
