Please use this identifier to cite or link to this item:
https://open.uns.ac.rs/handle/123456789/17966
Title: | Adaptive stochastic approximation algorithm | Authors: | Kresoja Milena Luzanin Zorana Stojkovska I. |
Issue Date: | 2017 | Journal: | Numerical Algorithms | Abstract: | © 2017, Springer Science+Business Media New York. 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: | https://open.uns.ac.rs/handle/123456789/17966 | ISSN: | 1017-1398 | DOI: | 10.1007/s11075-017-0290-4 |
Appears in Collections: | PMF Publikacije/Publications |
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.