Blanchet, J., & Si, N. (2019). Optimal uncertainty size in distributionally robust inverse covariance estimation. Operations Research Letters, 47(6), 618-621. https://doi.org/10.1016/j.orl.2019.10.005

View Publication

Abstract

In a recent paper, Nguyen et al. (2018) built a distributionally robust estimator for the precision matrix of the Gaussian distribution. The distributional uncertainty size is a key ingredient in the construction of this estimator. We develop a statistical theory which shows how to optimally choose the uncertainty size to minimize the associated Stein loss. Surprisingly, rather than the expected canonical square-root scaling rate, the optimal uncertainty size scales linearly with the sample size.

Authors
Jose Blanchet, Nian Si
Publication date
2019/11/1
Journal
Operations Research Letters
Volume
47
Issue
6
Pages
618-621
Publisher
North-Holland