no code implementations • 29 Sep 2021 • Dongkyu Lee, Ka Chun Cheung, Nevin Zhang
Overconfidence has been shown to impair generalization and calibration of a neural network.
no code implementations • 29 Sep 2021 • Zhiliang Tian, Yingxiu Zhao, Ziyue Huang, Yu-Xiang Wang, Nevin Zhang, He He
Differentially private (DP) learning algorithms provide guarantees on identifying the existence of a training sample from model outputs.