← Search

Mikko Heikkilä

2 accepted papers

2019

Differentially Private Markov Chain Monte Carlo

NeurIPS 2019spotlight

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 chai…

2017

Differentially private Bayesian learning on distributed data

NeurIPS 2017poster

Many applications of machine learning, for example in health care, would benefit from methods that can guarantee privacy of data subjects. Differential privacy (DP) has become established as a standard for protecting learning results. The standard DP algorithms require a single trusted party to have…