Topic
Stochastic Gradient Descent
Discover key takeaways from 2 podcast episodes about this topic.
Differential PrivacyPrivacy AmplificationMachine Learning
Jun 10, 2026Privacy Amplification for Correlated-Noise Mechanisms via b-Min-Sep Subsampling
This research introduces B-min-sep subsampling, a novel method that enhances privacy amplification for differentially private matrix factorization (DPMF) by leveraging correlated noise and enabling practical application in complex multi-attribution settings.
Machine LearningData PrivacyUnlearning Algorithms
Jan 27, 2026Leveraging Per-Instance Privacy for Machine Unlearning
This research reveals a theoretical and empirical framework for understanding and quantifying the difficulty of machine unlearning for individual data points, showing that unlearning steps scale logarithmically with per-instance privacy loss.
G
Google TechTalks