Stochastic gradient descent with differentially private updates

Differential privacy is a recent framework for computation on sensitive data, which has shown considerable promise in the regime of large datasets. Stochastic gradient methods are a popular approach for learning in the data-rich regime because they are computationally tractable and scalable. In this paper, we derive differentially private versions of stochastic gradient descent, and test them empirically. Our results show that standard SGD experiences high variability due to differential privacy, but a moderate increase in the batch size can improve performance significantly.