A geometric proximal gradient method for sparse least squares regression with probabilistic simplex constraint

DOI10.1007/S10915-022-01873-0zbMATH Open1492.65165arXiv2107.00809OpenAlexW3178578982MaRDI QIDQ2149159FDOQ2149159

Authors: Guiyun Xiao, Zheng-Jian Bai 

Publication date: 28 June 2022

Published in: Journal of Scientific Computing (Search for Journal in Brave)

Abstract: In this paper, we consider the sparse least squares regression problem with probabilistic simplex constraint. Due to the probabilistic simplex constraint, one could not apply the L1 regularization to the considered regression model. To find a sparse solution, we reformulate the least squares regression problem as a nonconvex and nonsmooth L1 regularized minimization problem over the unit sphere. Then we propose a geometric proximal gradient method for solving the regularized problem, where the explicit expression of the global solution to every involved subproblem is obtained. The global convergence of the proposed method is established under some mild assumptions. Some numerical results are reported to illustrate the effectiveness of the proposed algorithm.

Full work available at URL: https://arxiv.org/abs/2107.00809

Recommendations

• A proximal-gradient homotopy method for the sparse least-squares problem
• A preconditioned conjugate gradient method with active set strategy for \(\ell_1\)-regularized least squares
• An inexact projected gradient method for sparsity-constrained quadratic measurements regression
• Sparse solution of nonnegative least squares problems with applications in the construction of probabilistic Boolean networks.
• Stochastic proximal gradient method FOR \(\ell_1\) regularized optimization over a sphere

zbMATH Keywords

\(\ell_1\)-regularizationgeometric proximal gradient methodprobabilistic simplex constraintsparse least squares regression

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Convex programming (90C25) Nonconvex programming, global optimization (90C26)

Cites Work

• Title not available (Why is that?)
• Variational Analysis
• First-order methods in optimization
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
• Proximal alternating linearized minimization for nonconvex and nonsmooth problems
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Projection-like retractions on matrix manifolds
• Construction of probabilistic Boolean networks from a prescribed transition probability matrix: a maximum entropy rate approach.
• On modeling credit defaults: a probabilistic Boolean network approach
• Sparse solution of nonnegative least squares problems with applications in the construction of probabilistic Boolean networks.
• Efficient sparse semismooth Newton methods for the clustered Lasso problem
• Sparse probabilistic Boolean network problems: a partial proximal-type operator splitting method
• On construction of sparse probabilistic Boolean networks.

Cited In (1)

• Scaled proximal gradient methods for sparse optimization problems

This page was built for publication: A geometric proximal gradient method for sparse least squares regression with probabilistic simplex constraint

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2149159)