A Two-Stage Method for Constructing Linear Regressions Using Optimal Convex Combinations
- Authors: Senko O.V.1, Dokukin A.A.1, Kiselyova N.N.2, Khomutov N.Y.1
-
Affiliations:
- Dorodnicyn Computing Center, Federal Research Center “Computer Science and Control”
- Baikov Institute of Metallurgy and Materials Science
- Issue: Vol 97, No 2 (2018)
- Pages: 113-114
- Section: Mathematics
- URL: https://journals.rcsi.science/1064-5624/article/view/225470
- DOI: https://doi.org/10.1134/S1064562418020035
- ID: 225470
Cite item
Abstract
Multilevel learning systems have become more popular in pattern recognition and regression analysis. In this paper, a two-level method for constructing a multidimensional regression model is considered, in which a family of optimal convex combinations of simple one-dimensional least-square regressions is generated at the first level. The second level of the proposed learning system is given by an elastic net. Experimental verification presented demonstrate the efficiency of the proposed regression estimation method as applied to problems with a small amount of data.
About the authors
O. V. Senko
Dorodnicyn Computing Center, Federal Research Center “Computer Science and Control”
Email: dalex@ccas.ru
Russian Federation, Moscow, 119333
A. A. Dokukin
Dorodnicyn Computing Center, Federal Research Center “Computer Science and Control”
Author for correspondence.
Email: dalex@ccas.ru
Russian Federation, Moscow, 119333
N. N. Kiselyova
Baikov Institute of Metallurgy and Materials Science
Email: dalex@ccas.ru
Russian Federation, Moscow, 119991
N. Yu. Khomutov
Dorodnicyn Computing Center, Federal Research Center “Computer Science and Control”
Email: dalex@ccas.ru
Russian Federation, Moscow, 119333