Oracle Efficient Private Non-Convex Optimization

Understand

One of the most effective algorithms for differentially private learning and optimization is objective perturbation.

• This technique augments a given optimization problem (e.g.
• deriving from an ERM problem) with a random linear term, and then exactly solves it.
• However, to date, analyses of this approach crucially rely on the convexity and smoothness of the objective function, limiting its generality.