๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Convergence analysis of gradient descent stochastic algorithms

โœ Scribed by A. Shapiro; Y. Wardi

Publisher
Springer
Year
1996
Tongue
English
Weight
765 KB
Volume
91
Category
Article
ISSN
0022-3239

No coin nor oath required. For personal study only.

๐Ÿ“œ SIMILAR VOLUMES

Local minima escape transients by stocha
Local minima escape transients by stochastic gradient descent algorithms in blind adaptive equalizers
โœ Michael R. Frater; Robert R. Bitmead; C.Richard Johnson Jr ๐Ÿ“‚ Article ๐Ÿ“… 1995 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 638 KB

Many adaptive algorithms perform stochastic gradient descent on performance surfaces that are not guaranteed to be unimodal. In some examples, it is possible to show that not only is there more than one stationary point on this performance surface, but also that there is at least one incorrect local

Further results on almost sure convergen
Further results on almost sure convergence of the stochastic gradient algorithm
โœ Miloje S. Radenkovic ๐Ÿ“‚ Article ๐Ÿ“… 1999 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 151 KB ๐Ÿ‘ 2 views

In this paper, we consider the rate of convergence of the parameter estimation error and the cost function for the stochastic gradient-type algorithm. The problem is solved in the case of the minimum-variance stochastic adaptive control. It is proven that the cost function has the rate of convergenc

Convergence of stochastic gradient estim
Convergence of stochastic gradient estimation algorithm for multivariable ARX-like systems
โœ Yanjun Liu; Jie Sheng; Ruifeng Ding ๐Ÿ“‚ Article ๐Ÿ“… 2010 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 482 KB

This paper studies the convergence of the stochastic gradient identification algorithm of multi-input multi-output ARX-like systems (i.e., multivariable ARX-like systems) by using the stochastic martingale theory. This ARX-like model contains a characteristic polynomial and differs from the conventi