Premium
On a variable metric iterative method for solving the elastic net problem
Author(s) -
Liu Liya,
Qin Xiaolong,
Sahu D. R.
Publication year - 2020
Publication title -
mathematical methods in the applied sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.719
H-Index - 65
eISSN - 1099-1476
pISSN - 0170-4214
DOI - 10.1002/mma.7106
Subject(s) - mathematics , elastic net regularization , metric (unit) , hilbert space , iterative method , variable (mathematics) , gradient descent , descent (aeronautics) , mathematical optimization , metric space , method of steepest descent , net (polyhedron) , algorithm , mathematical analysis , computer science , artificial neural network , geometry , artificial intelligence , statistics , operations management , regression , engineering , economics , aerospace engineering
Based on a hybrid steepest‐descent method and a splitting method, we propose a variable metric iterative algorithm, which is useful in computing the elastic net solution. A solution theorem is established in the framework of Hilbert spaces. Numerical results are conducted on the signal processing to demonstrate the capacity and effectiveness of our algorithm.