Characterization of Overfitting in Robust Multiclass Classification
Jingyuan Xu · Weiwei Liu
2023 Poster
Abstract
This paper considers the following question: Given the number of classes m, the number of robust accuracy queries k, and the number of test examples in the dataset n, how much can adaptive algorithms robustly overfit the test dataset? We solve this problem by equivalently giving near-matching upper and lower bounds of the robust overfitting bias in multiclass classification problems.
Video
Chat is not available.
Successful Page Load