Continual Release Moment Estimation with Differential Privacy

From Google TechTalks · 43:57

Show by Google TechTalks

A Google TechTalk, 2025-04-16, presented by Nikita KalininPrivacy in ML Seminar. ABSTRACT: We propose Joint Moment Estimation (JME), a method for continually and privately estimating both the first and second moments of data with reduced noise compared to naive approaches. JME uses the matrix mechanism and a joint sensitivity analysis to allow the second moment estimation with no additional privacy cost, thereby improving accuracy while maintaining privacy. We demonstrate JME's effectiveness in two applications: estimating the running mean and covariance matrix for Gaussian density estimation, and model training with DP-Adam on CIFAR-10.Uploaded 26-01-26

More episodes of Google TechTalks

More episodes

PodSearch is a free, independent podcast search engine. Read about PodSearch, the privacy policy or contact us.