On the Convergence of Stochastic Aggregated Gradient Method
Turkish Journal of Mathematics and Computer Science · 2023
DOI: 10.47000/tjmcs.1037384 ↗Kurz gefasst
Fachartikel in der Zeitschrift Turkish Journal of Mathematics and Computer Science, 2023. Verfasst von Figen OZTOPRAK TOPKAYA. Die Arbeit nennt 8 Literaturangaben.
Abstract (Originalsprache)
The minimization problem of the sum of a large set of convex functions arises in various applications. Methods such as incremental gradient, stochastic gradient, and aggregated gradient are popular choices for solving those problems as they do not require a full gradient evaluation at every iteration. In this paper, we analyze a generalization of the stochastic aggregated gradient method via an alternative technique based on the convergence of iterative linear systems. The technique provides a short proof for the $O(\kappa^{-1})$ linear convergence rate in the quadratic case. We observe that the technique is rather restrictive for the general case, and can provide weaker results.
Zitieren
APA
TOPKAYA, F. O. (2023). On the Convergence of Stochastic Aggregated Gradient Method. Turkish Journal of Mathematics and Computer Science. https://doi.org/10.47000/tjmcs.1037384
Vancouver
TOPKAYA FO. On the Convergence of Stochastic Aggregated Gradient Method. Turkish Journal of Mathematics and Computer Science. 2023. doi:10.47000/tjmcs.1037384
BibTeX
@article{TOPKAYA2023,
author = {TOPKAYA, Figen OZTOPRAK},
title = {On the Convergence of Stochastic Aggregated Gradient Method},
journal = {Turkish Journal of Mathematics and Computer Science},
year = {2023},
doi = {10.47000/tjmcs.1037384}
}
EUVIMED