Optimization of the quantile criterion for the convex loss function by a stochastic quasigradient algorithm

A stochastic quasigradient algorithm is suggested for solving the quantile optimization problem with a convex loss function. The algorithm is based on stochastic finite-difference approximations of gradients of the quantile function by using the order statistics. The algorithm convergence almost sur...

Full description

Saved in:
Bibliographic Details
Published inAnnals of operations research Vol. 200; no. 1; p. 183
Main Authors Kibzun, Andrey, Matveev, Evgeniy
Format Journal Article
LanguageEnglish
Published Springer 01.11.2012
Online AccessGet full text
ISSN0254-5330
DOI10.1007/sl0479-011-0987-z

Cover

More Information
Summary:A stochastic quasigradient algorithm is suggested for solving the quantile optimization problem with a convex loss function. The algorithm is based on stochastic finite-difference approximations of gradients of the quantile function by using the order statistics. The algorithm convergence almost surely is proved.
ISSN:0254-5330
DOI:10.1007/sl0479-011-0987-z