Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.12188/6663
Title: Adaptive stochastic approximation algorithm
Authors: Kresoja, Milena
Lužanin, Zorana
Stojkovska, Irena 
Keywords: Unconstrained optimization
Stochastic optimization
Stochastic approximation
Noisy function
Adaptive step size
Gradient method
Descent direction
Issue Date: 27-Feb-2017
Publisher: Springer Science and Business Media LLC
Project: Ministry of Education, Science and Technology Development of Serbia grant no. 174030
Journal: Numerical Algorithms
Abstract: In this paper, stochastic approximation (SA) algorithm with a new adaptive step size scheme is proposed. New adaptive step size scheme uses a fixed number of previous noisy function values to adjust steps at every iteration. The algorithm is formulated for a general descent direction and almost sure convergence is established. The case when negative gradient is chosen as a search direction is also considered. The algorithm is tested on a set of standard test problems. Numerical results show good performance and verify efficiency of the algorithm compared to some of existing algorithms with adaptive step sizes.
URI: http://hdl.handle.net/20.500.12188/6663
DOI: 10.1007/s11075-017-0290-4
Appears in Collections:Faculty of Natural Sciences and Mathematics: Journal Articles

Show full item record

Page view(s)

14
checked on May 28, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.