88 citations · 176 across the 17 of their papers we have counts for
6 papers · 1 filter
Multiple Imputation via Generative Adversarial Network for High-dimensional Blockwise Missing Value Problems
Zongyu Dai, Zhiqi Bu, Qi Long
Missing data are present in most real world problems and need careful handling to preserve the prediction accuracy and statistical consistency in the downstream analysis. As the go…
Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability
Qiyiwen Zhang, Zhiqi Bu, Kan Chen +1
Bayesian neural network (BNN) allows for uncertainty quantification in prediction, offering an advantage over regular neural networks that has not been explored in the differential…
On the Convergence and Calibration of Deep Learning with Differential Privacy
Zhiqi Bu, Hua Wang, Zongyu Dai +1
Differentially private (DP) training preserves the data privacy usually at the cost of slower convergence (and thus lower accuracy), as well as more severe mis-calibration than its…
Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training?
Shuxiao Chen, Qinqing Zheng, Qi Long +1
A widely recognized difficulty in federated learning arises from the statistical heterogeneity among clients: local datasets often originate from distinct yet not entirely unrelate…
Federated -Differential Privacy
Qinqing Zheng, Shuxiao Chen, Qi Long +1
Federated learning (FL) is a training paradigm where the clients collaboratively learn models by repeatedly sharing information without compromising much on the privacy of their lo…
Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training
Cong Fang, Hangfeng He, Qi Long +1
In this paper, we introduce the \textit{Layer-Peeled Model}, a nonconvex yet analytically tractable optimization program, in a quest to better understand deep neural networks that…