Item Infomation
Title: | Adversarial classification via distributional robustness with Wasserstein ambiguity |
Authors: | Nam Ho-, Nguyen Stephen J., Wright |
Issue Date: | 2022 |
Publisher: | Springer |
Abstract: | We study a model for adversarial classification based on distributionally robust chance constraints. We show that under Wasserstein ambiguity, the model aims to minimize the conditional value-at-risk of the distance to misclassification, and we explore links to adversarial classification models proposed earlier and to maximum-margin classifiers. We also provide a reformulation of the distributionally robust model for linear classification, and show it is equivalent to minimizing a regularized ramp loss objective. |
Description: | CC BY |
URI: | https://link.springer.com/article/10.1007/s10107-022-01796-6 https://dlib.phenikaa-uni.edu.vn/handle/PNK/7460 |
Appears in Collections | OER - Khoa học Tự nhiên |
ABSTRACTS VIEWS
26
FULLTEXT VIEWS
1
Files in This Item: