High Dimensional Differentially Private Stochastic Optimization with Heavy-tailed Data

Understand

As one of the most fundamental problems in machine learning, statistics and differential privacy, Differentially Private Stochastic Convex Optimization (DP-SCO) has been extensively studied in recent years.

• However, most of the previous work can only handle either regular data distribution or irregular data in the low dimensional space case.
• To better understand the challenges arising from irregular data distribution, in this paper we provide the first study on the problem of DP-SCO with heavy-tailed data in the high dimensional space.
• In the first part we focus on the problem over some polytope constraint (such as the $\ell_1$-norm ball).