DETERMINATION OF ACCELERATED FACTORS IN GRADIENT DESCENT ITERATIONS BASED ON TAYLOR’S SERIES

Authors

Milena Petrović

Faculty of mathematics and natural sciences, University of Priština, Kosovska Mitrovica

Nataša Kontrec

Faculty of Natural Sciences and Mathematics, University of Pristina, Kosovska Mitrovica

Stefan Panić

0000-0002-5868-1764

Faculty of Sciences and Mathematics, University of Priština in Kosovska Mitrovica, Kosovska Mitrovica, Serbia

DOI 10.5937/univtho7-14337 Original page Cite this article

Keywords

convergence rate, quasi-Newton method, gradient descent methods, Line search

Abstract

In this paper the efficiency of accelerated gradient descent methods regarding the way of determination of accelerated factor is considered. Due to the previous researches we assert that the use of Taylor’s series of posed gradient descent iteration in calculation of accelerated parameter gives better final results than some other choices. We give a comparative analysis of efficiency of several methods with different approaches in obtaining accelerated parameter. According to the achieved results of numerical experiments we make a conclusion about the one of the most optimal way in defining accelerated parameter in accelerated gradient descent schemes.

Published

2017/07/17

Issue

Vol. 7 No. 1 (2017)

Section

Original Scientific Paper

Cite this article

Checking

Citation styles are being prepared.