Abstract

Recent research showed that most of the existing learning models are vulnerable to various privacy attacks. Thus, a major challenge facing the machine learning community is how to learn effectively from sensitive data. An effective way for this problem is to enforce differential privacy during the learning process. As a rigorous scheme for privacy preserving, Differential Privacy (DP) has now become a standard for private data analysis. Despite its rapid development in theory, DP's adoption to the machine learning community remains slow due to various challenges from the data, the privacy models and the learning tasks. In this talk, I will use the Empirical Risk Minimization (ERM) problem as an example and show how to overcome these challenges. Particularly, I will first talk about how to overcome the high dimensionality challenge from the data for Sparse Linear Regression in the local DP (LDP) model. Then, I will discuss the challenge from the non-interactive LDP model and show a series of results to reduce the exponential sample complexity of ERM. Next, I will present techniques on achieving DP for ERM with non-convex loss functions. Finally, I will discuss some future research along these directions.