Explore a concise 18-minute IEEE conference talk on locally differentially private sparse vector aggregation. Gain insights from experts Mingxun Zhou, Tianhao Wang, T-H. Hubert Chan, Giulia Fanti, and Elaine Shi as they discuss advanced techniques for preserving privacy in data aggregation. Learn about the challenges and solutions in handling sparse vectors while maintaining local differential privacy, a crucial aspect of modern data analysis and machine learning applications.
Locally Differentially Private Sparse Vector Aggregation
Overview
Syllabus
Locally Differentially Private Sparse Vector Aggregation
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
-
Locally Differentially Private Frequency Estimation Based on Convolution Framework
-
Locally Differentially Private Frequent Itemset Mining
-
Learning Differentially Private Mechanisms
-
A Theory to Instruct Differentially-Private Learning via Clipping Bias Reduction
-
Spectral-DP - Differentially Private Deep Learning through Spectral Perturbation and Filtering
-
Is Interaction Necessary for Distributed Private Learning?
