Browsing Mathematics (Faculty of) by Subject "Diffindo"
Now showing items 1-1 of 1
-
Differentially Private Learning with Noisy Labels
(University of Waterloo, 2020-05-28)Supervised machine learning tasks require large labelled datasets. However, obtaining such datasets is a difficult task and often leads to noisy labels due to human errors or adversarial perturbation. Recent studies have ...