Improving the Privacy-Utility Tradeoff in Differentially Private Machine Learning with Public Data
Offered By: Google TechTalks via YouTube
Course Description
Overview
Explore two innovative algorithms, DP-RAFT and DOPE-SGD, designed to enhance the privacy-utility tradeoff in Differentially Private Machine Learning using public data. Learn how these techniques leverage available public information to improve model accuracy while maintaining strong privacy guarantees. Discover the benefits of DP-RAFT for scenarios with ample public data for pretraining, and understand how DOPE-SGD utilizes advanced data augmentation to maximize limited public data resources. Gain insights into overcoming the challenges of gradient clipping and noise addition in Differentially Private Stochastic Gradient Descent (DP-SGD) to achieve better model performance without compromising privacy protection.
Syllabus
Improving the Privacy Utility Tradeoff in Differentially Private Machine Learning with Public Data
Taught by
Google TechTalks
Related Courses
TensorFlow を使った畳み込みニューラルネットワークDeepLearning.AI via Coursera Emotion AI: Facial Key-points Detection
Coursera Project Network via Coursera Transfer Learning for Food Classification
Coursera Project Network via Coursera Facial Expression Classification Using Residual Neural Nets
Coursera Project Network via Coursera Apply Generative Adversarial Networks (GANs)
DeepLearning.AI via Coursera