Solution of Nonconvex Nonsmooth Stochastic Optimization Problems

  • Authors:
  • Yu. M. Ermoliev;V. I. Norkin

  • Affiliations:
  • International Institute of Applied Systems Analysis, Laxenburg, Austria;Institute of Cybernetics, National Academy of Sciences of Ukraine, Kiev, Ukraine norkin@i.com.ua

  • Venue:
  • Cybernetics and Systems Analysis
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Different classes of nonconvex nonsmooth stochastic optimization problems are analyzed, their generalized differentiability properties and necessary optimality conditions are studied, and a technique for calculating stochastic gradients is developed. For each class of the problems, corresponding solution methods are proposed, in particular, generalizations of the stochastic quasigradient method.