Publications

BibTex format

@article{Anderson:2021:10.1287/ijoo.2021.0061,
author = {Anderson, E and Philpott, A},
doi = {10.1287/ijoo.2021.0061},
journal = {INFORMS Journal on Optimization},
pages = {90--124},
title = {Improving sample average approximation using distributional robustness},
url = {http://dx.doi.org/10.1287/ijoo.2021.0061},
volume = {4},
year = {2021}
}

Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - We consider stochastic optimization problems in which we aim to minimize the expected value of an objective function with respect to an unknown distribution of random parameters. We analyse the out-of-sampleperformance of solutions obtained by solving a distributionally robust version of the sample average approximation problem for unconstrained quadratic problems, and derive conditions under which these solutionsare improved in comparison with those of the sample average approximation. We compare different mechanisms for constructing a robust solution: phi-divergence using both total variation and standard smooth φfunctions; a CVaR-based risk measure; and a Wasserstein metric.
AU  - Anderson,E
AU  - Philpott,A
DO  - 10.1287/ijoo.2021.0061
EP  - 124
PY  - 2021///
SN  - 2575-1484
SP  - 90
TI  - Improving sample average approximation using distributional robustness
T2  - INFORMS Journal on Optimization
UR  - http://dx.doi.org/10.1287/ijoo.2021.0061
UR  - https://pubsonline.informs.org/doi/abs/10.1287/ijoo.2021.0061
UR  - http://hdl.handle.net/10044/1/89671
VL  - 4
ER  -

Download

ProfessorEdwardAnderson

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)