Transformed \(\ell_1\) regularization for learning sparse deep neural networks

DOI10.1016/J.NEUNET.2019.08.015zbMath1434.68512DBLPjournals/nn/MaMNZ19arXiv1901.01021OpenAlexW2970738028WikidataQ93198988 ScholiaQ93198988MaRDI QIDQ2185659

Yanyan Li

Publication date: 5 June 2020

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1901.01021

zbMATH Keywords

group sparsitydeep neural networksnon-convex regularizationtransformed \(\ell_1\)

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items (5)

On obtaining sparse semantic solutions for inverse problems, control, and neural network training ⋮ GSDAR: a fast Newton algorithm for \(\ell_0\) regularized generalized linear models with statistical guarantee ⋮ Nonconvex regularization for sparse neural networks ⋮ Consistent Sparse Deep Learning: Theory and Computation ⋮ A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networks

Uses Software

• glasso
• sparsenet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Nearly unbiased variable selection under minimax concave penalty
• A unified approach to model selection and sparse recovery using regularized least squares
• Computing sparse representation in a highly coherent dictionary based on difference of \(L_1\) and \(L_2\)
• Enhancing sparsity by reweighted \(\ell _{1}\) minimization
• Minimization of transformed \(L_1\) penalty: theory, difference of convex function algorithm, and robust application in compressed sensing
• Minimization of transformed \(l_1\) penalty: closed form representation and iterative thresholding algorithms
• Transformed Schatten-1 iterative thresholding algorithms for low rank matrix completion
• A Method for Finding Structured Sparse Solutions to Nonnegative Least Squares Problems with Applications
• SparseNet: Coordinate Descent With Nonconvex Penalties
• Deep Learning: Methods and Applications
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Local Strong Homogeneity of a Regularized Estimator
• Click Prediction for Web Image Reranking Using Multimodal Sparse Coding
• Multi-Modal Curriculum Learning for Semi-Supervised Image Classification
• Sparse Approximate Solutions to Linear Systems
• Minimization of $\ell_{1-2}$ for Compressed Sensing
• Model Selection and Estimation in Regression with Grouped Variables
• For most large underdetermined systems of linear equations the minimal 𝓁₁‐norm solution is also the sparsest solution

This page was built for publication: Transformed \(\ell_1\) regularization for learning sparse deep neural networks