Stochastic DCA for minimizing a large sum of DC functions with application to multi-class logistic regression
From MaRDI portal
Publication:2057761
Abstract: We consider the large sum of DC (Difference of Convex) functions minimization problem which appear in several different areas, especially in stochastic optimization and machine learning. Two DCA (DC Algorithm) based algorithms are proposed: stochastic DCA and inexact stochastic DCA. We prove that the convergence of both algorithms to a critical point is guaranteed with probability one. Furthermore, we develop our stochastic DCA for solving an important problem in multi-task learning, namely group variables selection in multi class logistic regression. The corresponding stochastic DCA is very inexpensive, all computations are explicit. Numerical experiments on several benchmark datasets and synthetic datasets illustrate the efficiency of our algorithms and their superiority over existing methods, with respect to classification accuracy, sparsity of solution as well as running time.
Recommendations
- Stochastic DCA for sparse multiclass logistic regression
- Novel DCA based algorithms for a special class of nonconvex problems with application in machine learning
- DCA based algorithms for feature selection in multi-class support vector machine
- Online learning based on online DCA and application to online classification
- DCA-based algorithms for DC fitting
Cites work
- A D.C. Optimization Algorithm for Solving the Trust-Region Subproblem
- A DC programming approach for feature selection in support vector machines learning
- A Stochastic Approximation Method
- Convex analysis approach to d. c. programming: Theory, algorithms and applications
- DC approximation approaches for sparse optimization
- DC programming and DCA: thirty years of developments
- Group variable selection via \(\ell_{p,0}\) regularization and application to optimal scoring
- scientific article; zbMATH DE number 3144846 (Why is no real title available?)
- scientific article; zbMATH DE number 4041643 (Why is no real title available?)
- scientific article; zbMATH DE number 3538599 (Why is no real title available?)
- scientific article; zbMATH DE number 1569102 (Why is no real title available?)
- scientific article; zbMATH DE number 2121575 (Why is no real title available?)
- Incremental majorization-minimization optimization with application to large-scale machine learning
- Incremental proximal methods for large scale convex optimization
- Minimizing finite sums with the stochastic average gradient
- Penalized classification using Fisher's linear discriminant
- Sparse covariance matrix estimation by DCA-based algorithms
- Sparse group Lasso and high dimensional multinomial classification
- Stochastic dual coordinate ascent methods for regularized loss minimization
- The DC (Difference of convex functions) programming and DCA revisited with DC models of real world nonconvex optimization problems
Cited in
(10)- Online learning based on online DCA and application to online classification
- Stochastic DCA for sparse multiclass logistic regression
- Stochastic difference-of-convex-functions algorithms for nonconvex programming
- Markov chain stochastic DCA and applications in deep learning with PDEs regularization
- Open issues and recent advances in DC programming and DCA
- A simple specification test for models with many conditional moment inequalities
- Stochastic variance-reduced majorization-minimization algorithms
- Federated learning with randomized alternating direction method of multipliers and application in training neural networks
- Contractive difference-of-convex algorithms
- Inexact proximal linearized algorithm for difference of convex composite functions
This page was built for publication: Stochastic DCA for minimizing a large sum of DC functions with application to multi-class logistic regression
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2057761)
