Distributed projection‐free algorithm for constrained aggregative optimization

In this paper, we focus on solving a distributed convex aggregative optimization problem in network, where each agent has its own cost function which depends not only decision variables but also the aggregated of all agents' variables. The variable is constrained within feasible set. order to minimize sum functions when knows local function, propose Frank–Wolfe algorithm based gradient tracking for node maintains two estimates, namely an estimate and global function. projection-free, involves linear get search direction at step. We show convergence proposed smooth objective over time-varying network. Finally, demonstrate computational efficiency via numerical simulations.