Explore the intricacies of differentially private multi-party data release for linear regression in this 57-minute Google TechTalk presented by Ruihan Wu. Delve into the Differential Privacy for ML Series as the speaker discusses advanced techniques for protecting privacy in collaborative data analysis scenarios. Gain insights into the challenges and solutions surrounding secure data sharing among multiple parties while maintaining statistical utility for linear regression tasks. Learn about cutting-edge approaches to balance privacy preservation with accurate model training in multi-party settings.
Differentially Private Multi-party Data Release for Linear Regression
Overview
Syllabus
Differentially Private Multi-party Data Release for Linear Regression
Taught by
Google TechTalks
Related Courses
-
Differentially Private Simple Linear Regression
-
Differentially Private Diffusion Models
-
Utility Analysis for Differentially-Private Pipelines
-
Small Space Differentially Private Graph Algorithms in the Continual Release Model
-
Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms
-
Generating Synthetic Tabular Data that is Differentially Private
