Optimization Online


Hypotheses testing on the optimal values of several risk-neutral or risk-averse convex stochastic programs and application to hypotheses testing on several risk measure values

Vincent Guigues (vincent.guigues***at***gmail.com)

Abstract: Given an arbitrary number of risk-averse or risk-neutral convex stochastic programs, we study hypotheses testing problems aiming at comparing the optimal values of these stochastic programs on the basis of samples of the underlying random vectors. We propose non-asymptotic tests based on confidence intervals on the optimal values of the stochastic programs obtained using the Robust Stochastic Approximation and the Stochastic Mirror Descent algorithms. When the objective functions are uniformly convex, we also propose a multi-step version of the Stochastic Mirror Descent algorithm and obtain confidence intervals on both the optimal values and optimal solutions. The results are applied to compare, using tests of hypotheses, the (extended polyhedral) risk measure values of several distributions.

Keywords: Stochastic Optimization; Risk measures; Hypothesis Testing; Multi-step Stochastic Mirror Descent; Robust Stochastic Approximation

Category 1: Stochastic Programming

Category 2: Convex and Nonsmooth Optimization (Convex Optimization )


Download: [PDF]

Entry Submitted: 07/24/2014
Entry Accepted: 07/24/2014
Entry Last Modified: 08/19/2014

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society