Group sparse optimization via _p,q regularization

MaRDI QIDQ5361291zbMATH OpenFDO

Authors Yaohua Hu, C. Li, Kaiwen Meng, Jing Qin, Xiao Qi Yang

Publication date 27 September 2017

Full work available at URL https://arxiv.org/abs/1601.07779, http://jmlr.csail.mit.edu/papers/v18/15-651.html

zbMATH Keywords

gene regulation networkgroup sparse optimizationiterative thresholding algorithmlower-order regularizationnonconvex optimizationproximal gradient methodrestricted eigenvalue condition

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Approximation methods and heuristics in mathematical programming (90C59)

Abstract: In this paper, we investigate a group sparse optimization problem via $el{l}_{p,q}$ regularization in three aspects: theory, algorithm and application. In the theoretical aspect, by introducing a notion of group restricted eigenvalue condition, we establish some oracle property and a global recovery bound of order $O(lambd{a}^{f}rac22-q)$ for any point in a level set of the $el{l}_{p,q}$ regularization problem, and by virtue of modern variational analysis techniques, we also provide a local analysis of recovery bound of order $O(lambd{a}^2)$ for a path of local minima. In the algorithmic aspect, we apply the well-known proximal gradient method to solve the $el{l}_{p,q}$ regularization problems, either by analytically solving some specific $el{l}_{p,q}$ regularization subproblems, or by using the Newton method to solve general $el{l}_{p,q}$ regularization subproblems. In particular, we establish the linear convergence rate of the proximal gradient method for solving the $el{l}_{1,q}$ regularization problem under some mild conditions. As a consequence, the linear convergence rate of proximal gradient method for solving the usual $el{l}_q$ regularization problem ($0<q<1$) is obtained. Finally in the aspect of application, we present some numerical results on both the simulated data and the real data in gene transcriptional regulation.

Recommendations

• The \(\ell_{2,q}\) regularized group sparse optimization: lower bound theory, recovery bound and algorithms
• Linear convergence of inexact descent method and inexact proximal gradient algorithms for lower-order regularization problems
• An efficient and globally convergent algorithm for \(\ell_{p,q} - \ell_r\) model in group sparse optimization
• On group-wise \(\ell_p\) regularization: theory and efficient algorithms
• Convergence rate analysis of proximal iteratively reweighted \(\ell_1\) methods for \(\ell_p\) regularization problems

Cited in

(57)

• On group-wise \(\ell_p\) regularization: theory and efficient algorithms
• An efficient and globally convergent algorithm for \(\ell_{p,q} - \ell_r\) model in group sparse optimization
• Modified inexact Levenberg-Marquardt methods for solving nonlinear least squares problems
• Linear convergence of inexact descent method and inexact proximal gradient algorithms for lower-order regularization problems
• Level-set subdifferential error bounds and linear convergence of Bregman proximal gradient method
• Nonconvex and nonsmooth sparse optimization via adaptively iterative reweighted methods
• A family of projection gradient methods for solving the multiple-sets split feasibility problem
• Computing the nearest polynomial to multiple given polynomials with a given zero via \(l_{2,q}\)-norm minimization
• RIP-based performance guarantee for low-tubal-rank tensor recovery
• Optimization problems involving group sparsity terms
• Proximal methods for reweighted \(l_Q\)-regularization of sparse signal recovery
• Sparse estimation via lower-order penalty optimization methods in high-dimensional linear regression
• Weak Sharp Minima for Convex Infinite Optimization Problems in Normed Linear Spaces
• Group-Sparse Signal Denoising: Non-Convex Regularization, Convex Optimization
• scientific article; zbMATH DE number 7594592 (Why is no real title available?)
• scientific article; zbMATH DE number 7626760 (Why is no real title available?)
• A Subspace Acceleration Method for Minimization Involving a Group Sparsity-Inducing Regularizer
• Nonconvex flexible sparsity regularization: theory and monotone numerical schemes
• Multiple-sets split quasi-convex feasibility problems: adaptive subgradient methods with convergence guarantee
• Difference-of-Convex Algorithms for a Class of Sparse Group \ell₀ Regularized Optimization Problems
• Computation of second-order directional stationary points for group sparse optimization
• Sparse optimization for nonconvex group penalized estimation
• scientific article; zbMATH DE number 7071841 (Why is no real title available?)
• Group Sparse Optimization for Images Recovery Using Capped Folded Concave Functions
• Solving constrained nonsmooth group sparse optimization via group Capped-\(\ell_1\) relaxation and group smoothing proximal gradient algorithm
• Local optimality for stationary points of group zero-norm regularized problems and equivalent surrogates
• Joint learning of multiple Granger causal networks via non-convex regularizations: inference of group-level brain connectivity
• A unified analysis of convex and non-convex \(\ell_p\)-ball projection problems
• A Regularized Newton Method for \({\boldsymbol{\ell}}_{q}\) -Norm Composite Optimization Problems
• A forward-backward algorithm with different inertial terms for structured non-convex minimization problems
• Relative Lipschitz-like Property of Parametric Systems via Projectional Coderivatives
• Proximal gradient method with extrapolation and line search for a class of non-convex and non-smooth problems
• Convergence rate of the relaxed CQ algorithm under Hölderian type error bound property
• A new algorithm for computing the nearest polynomial to multiple given polynomials via weighted \(\ell_{2, q}\)-norm minimization and its complex extension
• Continuous exact relaxation and alternating proximal gradient algorithm for partial sparse and partial group sparse optimization problems
• Group sparse structural smoothing recovery: model, statistical properties and algorithm
• Joint sparse optimization: lower-order regularization method and application in cell fate conversion
• Constrained mix sparse optimization via hard thresholding pursuit
• A proximal-gradient method for problems with overlapping group-sparse regularization: support identification complexity
• Relative well-posedness of truncated constrained systems accompanied by variational calculus
• Computing the proximal operator of the \(q\)-th power of the \(\ell_{1,q} \)-norm for group sparsity
• On convergence of iterative thresholding algorithms to approximate sparse solution for composite nonconvex optimization
• A step function based recursion method for 0/1 deep neural networks
• Iterative mix thresholding algorithm with continuation technique for mix sparse optimization and application
• Convergence analysis of iteratively reweighted _1 algorithms for computing the proximal operator of _p-norm
• Optimality conditions for group sparsity constrained optimization problems with equality and inequality constraints
• Minimization over the _p ball using a hybrid first-order method
• Avoiding strict saddle points of nonconvex regularized problems
• An exact penalty method for group-sparse portfolio selection
• General inertial smoothing Bregman proximal gradient algorithms for group capped-_1 regularized minimization
• Optimal group thresholding algorithms for group sparse optimization with convergence guarantee
• Recovery bounds for cardinality regularized optimization problem
• Group zero-norm regularized robust loss minimization: proximal MM method and statistical error bound
• Inexact online proximal mirror descent for time-varying composite optimization
• The \(\ell_{2,q}\) regularized group sparse optimization: lower bound theory, recovery bound and algorithms
• Group sparse optimization for learning predictive state representations
• The benefit of group sparsity

This page was built for publication: Group sparse optimization via \(\ell_{p,q}\) regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5361291)