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

DOI10.1007/s10479-011-0987-zzbMath1255.90090OpenAlexW2010055783MaRDI QIDQ1931654

Evgeniy Matveev, A. I. Kibzun

Publication date: 15 January 2013

Published in: Annals of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10479-011-0987-z

zbMATH Keywords

order statisticsquantile functionconvergence almost surelystochastic quasigradient algorithmquasiconcavity of the probability measurethe Minkowski inequality

Mathematics Subject Classification ID

Stochastic programming (90C15)

Related Items (1)

A Stochastic Approximation Method for Simulation-Based Quantile Optimization

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Brunn-Minkowski inequality and its aftermath
• Guaranteeing approach to solving quantile optimization problems
• Approximate distributions of order statistics. With applications to nonparametric statistics
• On extensions of the Brunn-Minkowski and Prekopa-Leindler theorems, including inequalities for log concave functions, and with an application to the diffusion equation
• On convexity of measures
• Convexity properties of probability and quantile functions in optimization problems
• A quasi-gradient algorithm for minimizing the quantile function
• On convergence of a stochastic quasigradient algorithm of quantile optimization
• \(\alpha\)-concave functions and measures and their applications
• Sufficient conditions for quasiconcavity of the probability function
• Order Statistics
• The Brunn-Minkowski inequality
• A Note on Quantiles in Large Samples

This page was built for publication: Optimization of the quantile criterion for the convex loss function by a stochastic quasigradient algorithm