Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6894535 | European Journal of Operational Research | 2018 | 12 Pages |
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,
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Science (General)
Authors
Dimitris Bertsimas, Martin S. Copenhaver,