Projects per year
Abstract
Generalized linear models (GLMs) such as logistic regression are among the most widely used arms in data analyst's repertoire and often used on sensitive datasets. A large body of prior works that investigate GLMs under differential privacy (DP) constraints provide only private point estimates of the regression coefficients, and are not able to quantify parameter uncertainty.
In this work, with logistic and Poisson regression as running examples, we introduce a generic noiseaware DP Bayesian inference method for a GLM at hand, given a noisy sum of summary statistics. Quantifying uncertainty allows us to determine which of the regression coefficients are statistically significantly different from zero. We provide a tight privacy analysis and experimentally demonstrate that the posteriors obtained from our model, while adhering to strong privacy guarantees, are close to the nonprivate posteriors.
Original language  English 

Title of host publication  Proceedings of the 38th International Conference on Machine Learning 
Editors  M Meila, T Zhang 
Pages  58385849 
Number of pages  12 
Publication status  Published  2021 
MoE publication type  A4 Article in a conference publication 
Event  International Conference on Machine Learning  Virtual, Online Duration: 18 Jul 2021 → 24 Jul 2021 Conference number: 38 
Publication series
Name  Proceedings of Machine Learning Research 

Publisher  PMLR 
Volume  139 
ISSN (Electronic)  26403498 
Conference
Conference  International Conference on Machine Learning 

Abbreviated title  ICML 
City  Virtual, Online 
Period  18/07/2021 → 24/07/2021 
Fingerprint
Dive into the research topics of 'Differentially Private Bayesian Inference for Generalized Linear Models'. Together they form a unique fingerprint.Projects
 1 Active

FIT: Federated probabilistic modelling for heterogeneous programmable IoT systems
Kaski, S., Kulkarni, T., Mallasto, A., Prediger, L. & Jälkö, J.
04/09/2019 → 31/12/2022
Project: Academy of Finland: Other research funding