Incremental subgradient methods for nondifferentiable optimization

Angelia Nedić, Dimitri P. Bertsekas

Research output: Contribution to journalArticle

381 Scopus citations

Abstract

We consider a class of subgradient methods for minimizing a convex function that consists of the sum of a large number of component functions. This type of minimization arises in a dual context from Lagrangian relaxation of the coupling constraints of large scale separable problems. The idea is to perform the subgradient iteration incrementally, by sequentially taking steps along the subgradients of the component functions, with intermediate adjustment of the variables after processing each component function. This incremental approach has been very successful in solving large differentiable least squares problems, such as those arising in the training of neural networks, and it has resulted in a much better practical rate of convergence than the steepest descent method. In this paper, we establish the convergence properties of a number of variants of incremental subgradient methods, including some that are stochastic. Based on the analysis and computational experiments, the methods appear very promising and effective for important classes of large problems. A particularly interesting discovery is that by randomizing the order of selection of component functions for iteration, the convergence rate is substantially improved.

Original languageEnglish (US)
Pages (from-to)109-138
Number of pages30
JournalSIAM Journal on Optimization
Volume12
Issue number1
DOIs
StatePublished - Jan 1 2002

Keywords

  • Convex programming
  • Incremental subgradient methods
  • Nondifferentiable optimization
  • Stochastic subgradient methods

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science

Fingerprint Dive into the research topics of 'Incremental subgradient methods for nondifferentiable optimization'. Together they form a unique fingerprint.

  • Cite this