Skip to main navigation Skip to search Skip to main content

Open-Loop Control: The Stochastic Gradient Method

  • École des ponts

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

The stochastic gradient method has a rather long history. The method foundations were given by (Robbins and Monro, Annals of Mathematical Statistics, 22:400-407, (1951) [129]) on the one hand, and by (Kiefer and Wolfowitz, Annals of Mathematical Statistics, 23:462-466, (1952) [93]) on the other. Later on, (Polyak, Automation and Remote Control, 37(12):1858-1868, (1976) [120], Polyak and Tsypkin, Automation and Remote Control, 40(3):378-389, (1979) [123]) gave results about the convergence rate. Based on this work, (Dodu et al., Bulletin de la Direction des Études et Recherches EDF, (1981) [57]) studied the optimality of the stochastic gradient algorithm, that is, the asymptotic efficiency of the associated estimator. An important contribution by (Polyak, Automation and Remote Control, 51(7):937-946, (1990) [121], Polyak and Juditsky, SIAM Journal on Control and Optimization, 30(4):838-855, (1992) [122]) has been to combine stochastic gradient method and averaging techniques in order to reach the optimal efficiency.

Original languageEnglish
Title of host publicationProbability Theory and Stochastic Modelling
PublisherSpringer Nature
Pages27-62
Number of pages36
DOIs
Publication statusPublished - 1 Jan 2015

Publication series

NameProbability Theory and Stochastic Modelling
Volume75
ISSN (Print)2199-3130
ISSN (Electronic)2199-3149

Keywords

  • Auxiliary Problem Principle
  • Open-loop Optimization Problem
  • Sample Average Approximation (SAA)
  • Stochastic Gradient Algorithm
  • Surely Convergent

Fingerprint

Dive into the research topics of 'Open-Loop Control: The Stochastic Gradient Method'. Together they form a unique fingerprint.

Cite this