Selective linearization for multi-block statistical learning

Yu Du

doi:10.1016/j.ejor.2020.12.010

Selective linearization for multi-block statistical learning

2021-08-01

1

PRE

AI

DOI：10.1016/j.ejor.2020.12.010

Original

Original request for help

Save

Abstract

En 中文

We consider the problem of minimizing a sum of several convex non-smooth functions and discuss the selective linearization method (SLIN), which iteratively linearizes all but one of the functions and employs simple proximal steps. The algorithm is a form of multiple operator splitting in which the order of processing partial functions is not fixed, but rather determined in the course of calculations. SLIN is globally convergent for an arbitrary number of component functions without artificial duplication of variables. We report results from extensive numerical experiments in two statistical learning settings such as large-scale overlapping group Lasso and doubly regularized support vector machine. In each setting, we introduce novel and efficient solutions for solving sub-problems. The numerical results demonstrate the efficacy and accuracy of SLIN. Published by Elsevier B.V.

Keywords:

Nonlinear programming

Statistical learning

Penalized regression

Regularized support vector machine

Selective linearization for multi-block statistical learning

Abstract

AI Summary

Journal

Organization