EconBase
← All papers

A data-driven approach to beating SAA out-of-sample

Jun-ya Gotoh, Michael Jong Kim, Andrew E. B. Lim

arXiv 26 May 2021 · Mathematics — Optimization · publishedOperations Research (2023) · 8 citations (OpenAlex)

arXiv:2105.12342 · PDF · DOI · OpenAlex · Extracted main text

Abstract

While solutions of Distributionally Robust Optimization (DRO) problems can sometimes have a higher out-of-sample expected reward than the Sample Average Approximation (SAA), there is no guarantee. In this paper, we introduce a class of Distributionally Optimistic Optimization (DOO) models, and show that it is always possible to “beat" SAA out-of-sample if we consider not just worst-case (DRO) models but also best-case (DOO) ones. We also show, however, that this comes at a cost: Optimistic solutions are more sensitive to model error than either worst-case or SAA optimizers, and hence are less robust and calibrating the worst- or best-case model to outperform SAA may be difficult when data is limited.

Citation extraction

29
references
60
in-text mentions
28
distinct cited
4
self-citations
12,038
main-text words

appendix boundary found by appendix_command · 70% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Gotoh, J., Kim, M.J., Lim, A.E.B (2020) Calibration of robust empirical optimization models self1.00064100%
2Lam, H (2021) On the Impossibility of Statistically Improving Empirical Optimization: A Second-Order Stochastic Dominance Perspective0.87492100%
3Anderson, E.J., Philpott, A (2020) Improving sample average approximation using distributional robustness0.87452100%
4Gotoh, J., Kim, M.J., Lim, A.E.B (2018) Robust empirical optimization is almost the same as mean-variance optimization self0.8307657%
5van der Vaart, A.W (2000) Asymptotic Statistics0.6443267%
6Nguyen, V.A., Shafieezadeh-Abadeh, S., Yue, M.C., Kuhn, D., Wieseman… (2019) Optimistic Distributionally Robust Optimization for Nonparametric Likelihood Approximation0.64422100%
7Gotoh, J., Kim, M.J., Lim, A.E.B (2020) Worst-case sensitivity self0.58531100%
8Kundhi, G., Rilstone, P (2008) The third order bias of nonlinear estimators0.5112250%
9Chen, L.L., Royset, J.O (2022) Rockafellian Relaxation in Optimization under Uncertainty: Asymptotically Exact Formulations (https://arxiv.org/abs/2204.04762)0.51121100%
10Duchi, J.C., Glynn, P.W., Namkoong, H (2016) Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach0.51121100%

Showing the top 10 of 28 scored citations.