Please use this identifier to cite or link to this item:
|Title:||Adaptive stochastic approximation algorithm||Authors:||Kresoja, Milena
Adaptive step size
|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
checked on May 28, 2020
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.