Convergence theory for nonconvex stochastic programming with an application to mixed logit

Fabian Bastin, Cinzia Cirillo, P.L. Toint

    Résultats de recherche: Contribution à un journal/une revueArticleRevue par des pairs

    176 Téléchargements (Pure)

    Résumé

    Monte Carlo methods have extensively been used and studied in the area of stochastic programming. Their convergence properties typically consider global minimizers or first-order critical points of the sample average approximation (SAA) problems and minimizers of the true problem, and show that the former converge to the latter for increasing sample size. However, the assumption of global minimization essentially restricts the scope of these results to convex problems. We review and extend these results in two directions: we allow for local SAA minimizers of possibly nonconvex problems and prove, under suitable conditions, almost sure convergence of local second-order solutions of the SAA problem to second-order critical points of the true problem. We also apply this new theory to the estimation of mixed logit models for discrete choice analysis. New useful convergence properties are derived in this context, both for the constrained and unconstrained cases, and associated estimates of the simulation bias and variance are proposed.
    langue originaleAnglais
    Pages (de - à)207-234
    Nombre de pages28
    journalMathematical Programming
    Volume108
    Numéro de publication2-3
    Les DOIs
    Etat de la publicationPublié - 1 juil. 2006

    Empreinte digitale Examiner les sujets de recherche de « Convergence theory for nonconvex stochastic programming with an application to mixed logit ». Ensemble, ils forment une empreinte digitale unique.

    Contient cette citation