Thông tin tài liệu
Nhan đề : | Adversarial classification via distributional robustness with Wasserstein ambiguity |
Tác giả : | Nam Ho-, Nguyen Stephen J., Wright |
Năm xuất bản : | 2022 |
Nhà xuất bản : | Springer |
Tóm tắt : | 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. |
Mô tả: | CC BY |
URI: | https://link.springer.com/article/10.1007/s10107-022-01796-6 https://dlib.phenikaa-uni.edu.vn/handle/PNK/7460 |
Bộ sưu tập | OER - Khoa học Tự nhiên |
XEM MÔ TẢ
26
XEM TOÀN VĂN
1
Danh sách tệp tin đính kèm: