On convergence of the stochastic subgradient method with on-line stepsize rules

Andrzej Ruszczyński; Wojciech Syski

doi:10.1016/0022-247X(86)90104-6

On convergence of the stochastic subgradient method with on-line stepsize rules

Andrzej Ruszczyński, Wojciech Syski

Research output: Contribution to journal › Article › peer-review

9 Scopus citations

Abstract

A stochastic subgradient method for solving convex stochastic programming problems is considered. New on-line rules for determining stepsizes are derived from the concept of local regularized improvement functions. Convergence with probability 1 of the whole method is established.

Original language	English (US)
Pages (from-to)	512-527
Number of pages	16
Journal	Journal of Mathematical Analysis and Applications
Volume	114
Issue number	2
DOIs	https://doi.org/10.1016/0022-247X(86)90104-6
State	Published - Mar 1986
Externally published	Yes

All Science Journal Classification (ASJC) codes

Analysis
Applied Mathematics

Access to Document

10.1016/0022-247X(86)90104-6

Cite this

@article{feb9a727785e43e6996be4c817b57341,

title = "On convergence of the stochastic subgradient method with on-line stepsize rules",

abstract = "A stochastic subgradient method for solving convex stochastic programming problems is considered. New on-line rules for determining stepsizes are derived from the concept of local regularized improvement functions. Convergence with probability 1 of the whole method is established.",

author = "Andrzej Ruszczy{\'n}ski and Wojciech Syski",

year = "1986",

month = mar,

doi = "10.1016/0022-247X(86)90104-6",

language = "English (US)",

volume = "114",

pages = "512--527",

journal = "Journal of Mathematical Analysis and Applications",

issn = "0022-247X",

publisher = "Academic Press Inc.",

number = "2",

}

TY - JOUR

T1 - On convergence of the stochastic subgradient method with on-line stepsize rules

AU - Ruszczyński, Andrzej

AU - Syski, Wojciech

PY - 1986/3

Y1 - 1986/3

N2 - A stochastic subgradient method for solving convex stochastic programming problems is considered. New on-line rules for determining stepsizes are derived from the concept of local regularized improvement functions. Convergence with probability 1 of the whole method is established.

AB - A stochastic subgradient method for solving convex stochastic programming problems is considered. New on-line rules for determining stepsizes are derived from the concept of local regularized improvement functions. Convergence with probability 1 of the whole method is established.

UR - http://www.scopus.com/inward/record.url?scp=0022676550&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022676550&partnerID=8YFLogxK

U2 - 10.1016/0022-247X(86)90104-6

DO - 10.1016/0022-247X(86)90104-6

M3 - Article

AN - SCOPUS:0022676550

SN - 0022-247X

VL - 114

SP - 512

EP - 527

JO - Journal of Mathematical Analysis and Applications

JF - Journal of Mathematical Analysis and Applications

IS - 2

ER -

On convergence of the stochastic subgradient method with on-line stepsize rules

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this