Junyuan Hong
Junyuan Hong
Home
Publications
Highlights
Projects
Posts
Light
Dark
Automatic
Dynamic Allocation
Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent
Protecting privacy in learning while maintaining the model performance has become increasingly critical in many applications that involve sensitive data. Private Gradient Descent (PGD) is a commonly used private learning framework, which noises …
Cite
×