Browsing University of Waterloo by Supervisor "He, Xi"
Now showing items 1-3 of 3
-
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 ... -
Differentially Private Online Aggregation
(University of Waterloo, 2022-01-13)Database operations are often performed in batch mode, i.e. the analyst issuing the query must wait till the database has been processed in its entirety before getting feedback. Batch mode is inadequate for large databases ... -
Unbiased Statistical Estimation and Valid Confidence Intervals Under Differential Privacy
(University of Waterloo, 2022-07-13)We present a method for producing unbiased parameter estimates and valid confidence intervals under the constraints of differential privacy, a formal framework for limiting individual information leakage from sensitive ...