skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Distributionally Robust Optimization with Correlated Data from Vector Autoregressive Processes

Abstract

We present a distributionally robust formulation of a stochastic optimization problem for non-i.i.d vector autoregressive data. We use the Wasserstein distance to define robustness in the space of distributions and we show, using duality theory, that the problem is equivalent to a finite convex-concave saddle point problem. The performance of the method is demonstrated on both synthetic and real data. (C) 2019 Elsevier B.V. All rights reserved.

Authors:
;
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
National Science Foundation (NSF); USDOE Office of Science - Office of Advanced Scientific Computing Research
OSTI Identifier:
1570433
DOE Contract Number:  
AC02-06CH11357
Resource Type:
Journal Article
Journal Name:
Operations Research Letters
Additional Journal Information:
Journal Volume: 47; Journal Issue: 4
Country of Publication:
United States
Language:
English
Subject:
Distributionally robust optimization; Saddle point problem; Wasserstein distance

Citation Formats

Dou, Xialiang, and Anitescu, Mihai. Distributionally Robust Optimization with Correlated Data from Vector Autoregressive Processes. United States: N. p., 2019. Web. doi:10.1016/j.orl.2019.04.005.
Dou, Xialiang, & Anitescu, Mihai. Distributionally Robust Optimization with Correlated Data from Vector Autoregressive Processes. United States. doi:10.1016/j.orl.2019.04.005.
Dou, Xialiang, and Anitescu, Mihai. Mon . "Distributionally Robust Optimization with Correlated Data from Vector Autoregressive Processes". United States. doi:10.1016/j.orl.2019.04.005.
@article{osti_1570433,
title = {Distributionally Robust Optimization with Correlated Data from Vector Autoregressive Processes},
author = {Dou, Xialiang and Anitescu, Mihai},
abstractNote = {We present a distributionally robust formulation of a stochastic optimization problem for non-i.i.d vector autoregressive data. We use the Wasserstein distance to define robustness in the space of distributions and we show, using duality theory, that the problem is equivalent to a finite convex-concave saddle point problem. The performance of the method is demonstrated on both synthetic and real data. (C) 2019 Elsevier B.V. All rights reserved.},
doi = {10.1016/j.orl.2019.04.005},
journal = {Operations Research Letters},
number = 4,
volume = 47,
place = {United States},
year = {2019},
month = {7}
}