1 citations · 1 across the 8 of their papers we have counts for
11 papers
Knockoffs-based False Discovery Rate Control and Simplification for Deep Neural Networks
Wenyu Liao, Yiqing Shi, Fang Xie
The deep neural network is a widely used framework in machine learning that has been widely applied in various fields. However, deep neural networks often involve a large number of…
Revisiting Privacy Amplification by Subsampling in Selective Release DPSGD
Xiaobo Huang, Fang Xie
Machine learning's reliance on sensitive data necessitates privacy-preserving techniques like Differentially Private Stochastic Gradient Descent (DPSGD). However, DPSGD suffers fro…
When Do Fewer Coordinates Suffice in DP-SGD?
Huiqi Zhang, Fang Xie
Differentially private stochastic gradient descent (DP-SGD) injects noise into every updated coordinate, making the injected noise energy scale with the ambient parameter dimension…
Steps Adaptive Decay DPSGD: Enhancing Performance on Imbalanced Datasets with Differential Privacy with HAM10000
Xiaobo Huang, Fang Xie
When applying machine learning to medical image classification, data leakage is a critical issue. Previous methods, such as adding noise to gradients for differential privacy, work…
AdaDPIGU: Differentially Private SGD with Adaptive Clipping and Importance-Based Gradient Updates for Deep Neural Networks
Huiqi Zhang, Fang Xie
Differential privacy has been proven effective for stochastic gradient descent; however, existing methods often suffer from performance degradation in high-dimensional settings, as…
LH2Face: Loss function for Hard High-quality Face
Fan Xie, Yang Wang, Yikang Jiao +3
In current practical face authentication systems, most face recognition (FR) algorithms are based on cosine similarity with softmax classification. Despite its reliable classificat…