Andy Dong

Google Research & TechTalks

1 standalone talk · 1 total lecture · 1h recorded

Algorithms & Theoretical CS AI & Machine Learning

Standalone talks by Andy Dong

Self-contained public lectures, keynote addresses, and research seminars.

Privacy Amplification for Correlated-Noise Mechanisms via b-Min-Sep Subsampling

57:54

Theory & Algos·Research Seminar

Privacy Amplification for Correlated-Noise Mechanisms via b-Min-Sep Subsampling

Andy Dong·Google Research & TechTalks

A rigorous examination of privacy amplification techniques for correlated-noise mechanisms, introducing b-min-sep subsampling as a novel batching scheme for DP-MF. Explores advanced topics in private model training.