A1 Journal article (refereed)
A Douglas–Rachford method for sparse extreme learning machine (2019)


Kärkkäinen, Tommi; Glowinski, Roland (2019). A Douglas–Rachford method for sparse extreme learning machine. Methods and Applications of Analysis, 26 (3), 217-234. DOI: 10.4310/MAA.2019.v26.n3.a1


JYU authors or editors


Publication details

All authors or editors: Kärkkäinen, Tommi; Glowinski, Roland

Journal or series: Methods and Applications of Analysis

ISSN: 1073-2772

eISSN: 1945-0001

Publication year: 2019

Volume: 26

Issue number: 3

Pages range: 217-234

Publisher: International Press

Publication country: United States

Publication language: English

DOI: http://doi.org/10.4310/MAA.2019.v26.n3.a1

Open Access: Publication channel is not openly available


Abstract

Operator-splitting methods have gained popularity in various areas of computational sciences, including machine learning. In this article, we present a novel nonsmooth and nonconvex formulation and its efficient associated solution algorithm to derive a sparse predictive machine learning model. The model structure is based on the so-called extreme learning machine with randomly generated basis. Our computational experiments confirm the efficiency of the proposed method, when a bold selection of the timestep is made. Comparative tests also indicate interesting results concerning the use of the l0 seminorm for ultimate sparsity.


Keywords: machine learning; mathematical optimisation

Free keywords: operator-splitting; Douglas–Rachford; extreme learning machine; sparse regularization


Contributing organizations


Ministry reporting: Yes

Reporting Year: 2020

Preliminary JUFO rating: 1


Last updated on 2020-09-07 at 23:09