SGD on Random Mixtures: Private Machine Learning under Data Breach Threats

We propose Stochastic Gradient Descent on Random Mixtures (SGDRM) as a simple way of protecting data under data breach threats. We show that SGDRM converges to the globally optimal point for deep neural networks with linear activations while being differentially private. We also train nonlinear neural networks with private mixtures as the training data, proving the practicality of SGDRM.