Differentially Private Markov Chain Monte Carlo

Mikko Heikkilä, Joonas Jälkö, Onur Dikmen, Antti Honkela

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu


Recent developments in differentially private (DP) machine learning and DP Bayesian learning have enabled learning under strong privacy guarantees for the training data subjects. In this paper, we further extend the applicability of DP Bayesian learning by presenting the first general DP Markov chain Monte Carlo (MCMC) algorithm whose privacy-guarantees are not subject to unrealistic assumptions on Markov chain convergence and that is applicable to posterior inference in arbitrary models. Our algorithm is based on a decomposition of the Barker acceptance test that allows evaluating the Rényi DP privacy cost of the accept-reject choice. We further show how to improve the DP guarantee through data subsampling and approximate acceptance tests.
Otsikko33rd Conference on Neural Information Processing Systems
AlaotsikkoNeurIPS 2019
KustantajaNeural Information Processing Systems Foundation
TilaJulkaistu - 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaConference on Neural Information Processing Systems - Vancouver, Kanada
Kesto: 8 joulukuuta 201914 joulukuuta 2019
Konferenssinumero: 33


NimiAdvances in Neural Information Processing Systems
ISSN (elektroninen)1049-5258


ConferenceConference on Neural Information Processing Systems

Sormenjälki Sukella tutkimusaiheisiin 'Differentially Private Markov Chain Monte Carlo'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

  • Siteeraa tätä

    Heikkilä, M., Jälkö, J., Dikmen, O., & Honkela, A. (2019). Differentially Private Markov Chain Monte Carlo. teoksessa 33rd Conference on Neural Information Processing Systems: NeurIPS 2019 (Advances in Neural Information Processing Systems). Neural Information Processing Systems Foundation.