EconBase
← All papers

Worst-case sensitivity

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

arXiv 21 Oct 2020 · Econometrics

arXiv:2010.10794 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We introduce the notion of Worst-Case Sensitivity, defined as the worst-case rate of increase in the expected cost of a Distributionally Robust Optimization (DRO) model when the size of the uncertainty set vanishes. We show that worst-case sensitivity is a Generalized Measure of Deviation and that a large class of DRO models are essentially mean-(worst-case) sensitivity problems when uncertainty sets are small, unifying recent results on the relationship between DRO and regularized empirical optimization with worst-case sensitivity playing the role of the regularizer. More generally, DRO solutions can be sensitive to the family and size of the uncertainty set, and reflect the properties of its worst-case sensitivity. We derive closed-form expressions of worst-case sensitivity for well known uncertainty sets including smooth $\phi$-divergence, total variation, "budgeted" uncertainty sets, uncertainty sets corresponding to a convex combination of expected value and CVaR, and the Wasserstein metric. These can be used to select the uncertainty set and its size for a given application.

Citation extraction

31
references
60
in-text mentions
31
distinct cited
6
self-citations
10,279
main-text words

appendix boundary found by appendix_command · 71% 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
1Jun-ya Gotoh, Michael Jong Kim, and Andrew E.B. Lim (2018) Robust empirical optimization is almost the same as mean–variance optimization self0.9507486%
2R. Tyrrell Rockafellar, Stan Uryasev, and Michael Zabarankin (2006) Generalized deviations in risk analysis0.92844100%
3Jose Blanchet, Yang Kang, and Karthyek Murthy (2019) Robust Wasserstein profile inference and applications to machine learning0.81142100%
4Rui Gao, Xi Chen, and Anton J Kleywegt (2017) Wasserstein distributional robustness and regularization in statistical learning0.81142100%
5David G. Luenberger (1997) Optimization by Vector Space Methods0.7375260%
6Soroosh Shafieezadeh-Abadeh, Peyman Mohajerin Esfahani, and Daniel K… (2015) Distributionally robust logistic regression0.7374275%
7Henry Lam (2016) Robust sensitivity analysis for stochastic systems0.64422100%
8Jun-ya Gotoh, Michael Jong Kim, and Andrew E.B. Lim (2020) Calibration of distributionally robust empirical optimization models self0.58531100%
9John C. Duchi and Hongseok Namkoong (2019) Variance-based regularization with convex objectives0.51121100%
10Huan Xu, Constantine Caramanis, and Shie Mannor (2010) Robust regression and Lasso0.51121100%

Showing the top 10 of 31 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1A data-driven approach to beating SAA out-of-sample0.58531