Convergence analysis of gradient descent stochastic algorithms (Q1359455): Difference between revisions
From MaRDI portal
Added link to MaRDI item. |
Removed claim: reviewed by (P1447): Item:Q1164012 |
||
Property / reviewed by | |||
Property / reviewed by: Yousri M. Abd-El-Fattah / rank | |||
Revision as of 12:31, 22 February 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Convergence analysis of gradient descent stochastic algorithms |
scientific article |
Statements
Convergence analysis of gradient descent stochastic algorithms (English)
0 references
7 October 1997
0 references
The paper provides convergence analysis results for a sample-path based stochastic gradient-descent algorithm for optimizing expected-value performance measures in discrete event systems. The algorithm requires that the distance between two consecutive iteration points converge to zero as the iterate count goes to infinity. The paper gives two convergence results: one for the case where the expected-value function is continuously differentiable and the other when the function is nondifferentiable but the sample performance functions are convex. The proofs are based on a version of the uniform law of large numbers which is provable for many discrete event systems where infinitesimal perturbation analysis is known to be strongly consistent.
0 references
gradient descent
0 references
uniform law of large numbers
0 references
infinitesimal
0 references
discrete event systems
0 references