Distributed Online Learning Algorithm With Differential Privacy Strategy for Convex Nondecomposable Global Objectives. (arXiv:2206.07944v2 [math.OC] UPDATED)

In this paper, we deal with a general distributed constrained online learning
problem with privacy over time-varying networks, where a class of
nondecomposable objective functions are considered. Under this setting, each
node only controls a part of the global decision variable, and the goal of all
nodes is to collaboratively minimize the global objective over a time horizon
$T$ while guarantees the security of the transmitted information. For such
problems, we first design a novel generic algorithm framework, named as …

algorithm differential privacy distributed global math objectives online learning privacy strategy