Conference Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 294 - SPEED: Statistics in Social Sciences and Survey Research Part 2
Type: Contributed
Date/Time: Tuesday, August 9, 2022 : 10:30 AM to 11:15 AM
Sponsor: Business and Economic Statistics Section
Abstract #323789
Title: Privacy Secure Aggregation of the Individual Models into a Federated Model with Bayesian MCMC Bootstrapping
Author(s): Eugene Yankovsky* and Ana Yankovsky
Companies: EY and Inuitive Surgical
Keywords: privacy protection; federated model; Bayesian MCMC; bootstrapping; Monte Carlo Markov Chain methods; Differential Privacy
Abstract:

The Bayesian MCMC bootstrapping approach provides a viable alternative to the classic Differential Privacy protection approach (Dwork and Roth (2014)) by random sampling of the individual models’ tuples of their coefficients, standard errors, the training sample sizes and aggregating them into one federated model. In this way, this method provides the data source privacy protection without hurting the model’s predictive power that is unavoidable result of adding Differential Privacy random noise to the model’s training data set.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2022 program