Please use this identifier to cite or link to this item:
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.
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)

checked on May 28, 2020

Google ScholarTM



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