Stochastic approximation with adaptive step sizes for optimization in noisy environment and its application in regression models

Journal
Matematichki Bilten
Date Issued
2017-01-01
Author(s)
Kresoja, Milena
Dimovski, Marko
Luzanin, Zorana
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.
Subjects

unconstrained optimiz...

File(s)
Loading...
Thumbnail Image
Name

STOCHASTIC APPROXIMATION WITH ADAPTIVE STEP SIZES FOR OPTIMIZATION IN NOISY ENVIRONMENT AND ITS APPLICATION IN REGRESSION MODELS.pdf

Description
Journal Article
Size

192.74 KB

Format

Adobe PDF

Checksum

(MD5):791a3b4f8d53097a0f8e69e02fe02524