DP-LSSGD: A Stochastic Optimization Method to Lift the Utility in Privacy-Preserving ERM

1 code implementation • 28 Jun 2019 • Bao Wang, Quanquan Gu, March Boedihardjo, Farzin Barekat, Stanley J. Osher

At the core of DP-LSSGD is the Laplacian smoothing, which smooths out the Gaussian noise used in the Gaussian mechanism.

Privacy Preserving Stochastic Optimization

Laplacian Smoothing Gradient Descent

1 code implementation • 17 Jun 2018 • Stanley Osher, Bao Wang, Penghang Yin, Xiyang Luo, Farzin Barekat, Minh Pham, Alex Lin

We propose a class of very simple modifications of gradient descent and stochastic gradient descent.