STOCHASTIC APPROXIMATION WITH ADAPTIVE STEP SIZES FOR OPTIMIZATION IN NOISY ENVIRONMENT AND ITS APPLICATION

Authors

DOI:

https://doi.org/10.37560/matbil11700062k

Keywords:

unconstrained optimization, stochastic optimization, stochastic approximation, noisy function, adaptive step size, gradient method, descent direction, regression models

Abstract

We propose a generalization of recently proposed stochastic approximation method with adaptive step sizes for optimization problems in noisy environment. The adaptive step size scheme uses only a predefined number of last noisy functional values to select a step size for the next iterate and allows different intensities of influence of the past functional values. The almost sure convergence is established under suitable assumptions. Numerical results indicate a good performance of the method. Application of the method in regression models is presented.

Downloads

Published

2017-01-01

Issue

Vol. 41 No. 1 (2017): 41 (LXVII) 1 (2017)

Section

Articles

License

Copyright (c) 2017 Matematichki Bilten

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
M. Kresoja, M. Dimovski, I. Stojkovska, and Z. Lužanin, “STOCHASTIC APPROXIMATION WITH ADAPTIVE STEP SIZES FOR OPTIMIZATION IN NOISY ENVIRONMENT AND ITS APPLICATION”, Mat. Bilt., vol. 41, no. 1, pp. 62–79, Jan. 2017, doi: 10.37560/matbil11700062k.