Completed
Summary of Contributions
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Private Convex Optimization via Exponential Mechanism - Differential Privacy for Machine Learning
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 One-sentence Summary
- 3 Differential Privacy
- 4 Noisy SGD
- 5 Regularized Exponential Mechanism (RegEM)
- 6 Isoperimetric Inequality for strongly log- concave measures
- 7 Concentration bounds for Lipschitz functions
- 8 Proof Sketch
- 9 Utility Analysis
- 10 A Question from the Duck
- 11 DP-Stochastic Convex Optimization (SCO)
- 12 Intuition
- 13 Open Problems
- 14 RegEM Revisited
- 15 Bounding Generalization Error
- 16 Bound Wasserstein Distance
- 17 Bounding KL. divergence
- 18 Bounding Population Loss
- 19 Summary of Contributions
- 20 A new sampling algorithm
- 21 Algorithms for DP-ERM and DP-SCO
