Characterization of the equivalence of robustification and regularization in linear and matrix regression
Name
Bertsimas_Characterization of the.pdf
Description
Submitted version
Size
303.59 KB
Format
Unknown
Checksum (MD5)
5436d75fcaab426ec3283c1b0df9bfe8
Author(s)
Bertsimas, Dimitris J
Copenhaver, Martin Steven
Date Issued
2018
Journal
European Journal of Operational Research
Publisher
Elsevier BV
Version
Original manuscript
Abstract
The notion of developing statistical methods in machine learning which are robust to adversarial perturbations in the underlying data has been the subject of increasing interest in recent years. A common feature of this work is that the adversarial robustification often corresponds exactly to regularization methods which appear as a loss function plus a penalty. In this paper we deepen and extend the understanding of the connection between robustification and regularization (as achieved by penalization) in regression problems. Specifically, (a) In the context of linear regression, we characterize precisely under which conditions on the model of uncertainty used and on the loss function penalties robustification and regularization are equivalent.(b) We extend the characterization of robustification and regularization to matrix regression problems (matrix completion and Principal Component Analysis).
MIT Department
Sloan School of Management
Massachusetts Institute of Technology. Operations Research Center
Terms of Use
Creative Commons Attribution-NonCommercial-NoDerivs License
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1016/J.EJOR.2017.03.051
