Differentially Private Statistical Inference through -Divergence One Posterior Sampling

JE Jewson, S Ghalebikesabi… - Advances in Neural …, 2023‏ - proceedings.neurips.cc
Differential privacy guarantees allow the results of a statistical analysis involving sensitive
data to be released without compromising the privacy of any individual taking part …

DP-Fast MH: Private, fast, and accurate Metropolis-Hastings for large-scale Bayesian inference

W Zhang, R Zhang - International Conference on Machine …, 2023‏ - proceedings.mlr.press
Bayesian inference provides a principled framework for learning from complex data and
reasoning under uncertainty. It has been widely applied in machine learning tasks such as …

Statistic selection and MCMC for differentially private Bayesian estimation

B Alparslan, S Yıldırım - Statistics and Computing, 2022‏ - Springer
This paper concerns differentially private Bayesian estimation of the parameters of a
population distribution, when a noisy statistic of a sample from that population is shared to …

Differentially private online Bayesian estimation with adaptive truncation

S Yildirim - Turkish Journal of Electrical Engineering and …, 2024‏ - journals.tubitak.gov.tr
In this paper, a novel online and adaptive truncation method is proposed for differentially
private Bayesian online estimation of a static parameter regarding a population. A local …

[PDF][PDF] Robustness-Privacy Trade-Off In Bayesian Neural Networks

M Ghitu, M Wicker, W Knottenbelt - 2024‏ - imperial.ac.uk
Substantial developments have recently been made to devise provable methods that ensure
the trustworthiness of deep neural networks. Most of these pieces of work study properties …

[PDF][PDF] Differentially private and distributed Bayesian learning

M Heikkilä - 2023‏ - mixheikk.github.io
Abstract Machine learning aims to learn patterns from data. When the data are about people,
a machine learning model will learn information about people. Such models can be used by …

Monte Carlo Methods For Data Privacy Applications

B Alparslan - 2023‏ - research.sabanciuniv.edu
This thesis focuses on data privacy applications with Bayesian inference, particularly Markov
chain Monte Carlo (MCMC) methods for two main data privacy problems. Firstly, we focus on …