Data Augmentation MCMC for Bayesian Inference from Privatized Data

Data Augmentation MCMC for Bayesian Inference from Privatized Data

Fields Institute via YouTube Direct link

Intro

1 of 18

1 of 18

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Data Augmentation MCMC for Bayesian Inference from Privatized Data

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Privacy: a challenge in modern data curation
  3. 3 The U.S. Census Bureau adopts differential privacy
  4. 4 The mechanism of differential privacy
  5. 5 Differential privacy: benefits and challenges
  6. 6 Situating our (statistical x privacy) framework
  7. 7 Statistical inference from privatized data
  8. 8 Existing solutions
  9. 9 A traditional Gibbs sampler
  10. 10 A general Metropolis-within Gibbs sampler
  11. 11 Requirements, run time, and efficiency
  12. 12 Ergodicity of the proposed sampler
  13. 13 Application: a naïve Bayes classifier
  14. 14 Simulation setup
  15. 15 Posterior mean
  16. 16 Frequentist coverage
  17. 17 Empirical acceptance rates
  18. 18 Summary

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.