3 papers
cs.LG2019
Renyi Differentially Private ADMM for Non-Smooth Regularized Optimization
Chen Chen, Jaewoo Lee
In this paper we consider the problem of minimizing composite objective functions consisting of a convex differentiable loss function plus a non-smooth regularization term, such as…
cs.LG2018
Concentrated Differentially Private Gradient Descent with Adaptive per-Iteration Privacy Budget
Jaewoo Lee, Daniel Kifer
Iterative algorithms, like gradient descent, are common tools for solving a variety of problems, such as model fitting. For this reason, there is interest in creating differentiall…
cs.LG2018
Differentially Private Confidence Intervals for Empirical Risk Minimization
Yue Wang, Daniel Kifer, Jaewoo Lee
The process of data mining with differential privacy produces results that are affected by two types of noise: sampling noise due to data collection and privacy noise that is desig…