Privacy-aware variational inference

Show full item record

Title: Privacy-aware variational inference
Author: Jälkö, Joonas
Other contributor: Helsingin yliopisto, Matemaattis-luonnontieteellinen tiedekunta, Matematiikan ja tilastotieteen laitos
University of Helsinki, Faculty of Science, Department of Mathematics and Statistics
Helsingfors universitet, Matematisk-naturvetenskapliga fakulteten, Institutionen för matematik och statistik
Publisher: Helsingfors universitet
Date: 2017
Language: eng
Thesis level: master's thesis
Discipline: Tillämpad matematik
Applied Mathematics
Soveltava matematiikka
Abstract: This thesis focuses on privacy-preserving statistical inference. We use a probabilistic point of view of privacy called differential privacy. Differential privacy ensures that replacing one individual from the dataset with another individual does not affect the results drastically. There are different versions of the differential privacy. This thesis considers the ε-differential privacy also known as the pure differential privacy, and also a relaxation known as the (ε, δ)-differential privacy. We state several important definitions and theorems of DP. The proofs for most of the theorems are given in this thesis. Our goal is to build a general framework for privacy preserving posterior inference. To achieve this we use an approximative approach for posterior inference called variational Bayesian (VB) methods. We build the basic concepts of variational inference with certain detail and show examples on how to apply variational inference. After giving the prerequisites on both DP and VB we state our main result, the differentially private variational inference (DPVI) method. We use a recently proposed doubly stochastic variational inference (DSVI) combined with Gaussian mechanism to build a privacy-preserving method for posterior inference. We give the algorithm definition and explain its parameters. The DPVI method is compared against the state-of-the-art method for DP posterior inference called the differentially private stochastic gradient Langevin dynamics (DP-SGLD). We compare the performance on two different models, the logistic regression model and the Gaussian mixture model. The DPVI method outperforms DP-SGLD in both tasks.
Subject: Differential privacy
Variational Bayesian methods
Machine learning
Bayesian inference

Files in this item

Total number of downloads: Loading...

Files Size Format View
gradu_final_J_Jalko.pdf 668.5Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record