Optimization of the quantile criterion for the convex loss function by a stochastic quasigradient algorithm |
| |
Authors: | Andrey Kibzun Evgeniy Matveev |
| |
Affiliation: | 1. Moscow Aviation Institute, Volokolamskoe Shosse 4, Moscow, 125871, Russia
|
| |
Abstract: | 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. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |