Private Convex Optimization via Exponential Mechanism - Differential Privacy for Machine Learning

Private Convex Optimization via Exponential Mechanism - Differential Privacy for Machine Learning

Google TechTalks via YouTube Direct link

Intuition

12 of 21

12 of 21

Intuition

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. 1 Intro
  2. 2 One-sentence Summary
  3. 3 Differential Privacy
  4. 4 Noisy SGD
  5. 5 Regularized Exponential Mechanism (RegEM)
  6. 6 Isoperimetric Inequality for strongly log- concave measures
  7. 7 Concentration bounds for Lipschitz functions
  8. 8 Proof Sketch
  9. 9 Utility Analysis
  10. 10 A Question from the Duck
  11. 11 DP-Stochastic Convex Optimization (SCO)
  12. 12 Intuition
  13. 13 Open Problems
  14. 14 RegEM Revisited
  15. 15 Bounding Generalization Error
  16. 16 Bound Wasserstein Distance
  17. 17 Bounding KL. divergence
  18. 18 Bounding Population Loss
  19. 19 Summary of Contributions
  20. 20 A new sampling algorithm
  21. 21 Algorithms for DP-ERM and DP-SCO

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.