Differentially Private Bayesian Inference for Generalized Linear Models

         Tejas Kulkarni 1 Joonas Jalko 1 Antti Koskela 2 Samuel Kaski 1 3 Antti Honkela 2

             Abstract                  on the regression coefficients, such as determining which
   Generalized linear models (GLMs) such as logis-         coefficients can be confidently inferred to be different from
   tic regression are among the most widely used          zero.
   arms in data analyst’s repertoire and often used  ...