Elham Monifi - Faculty of Mathematical Sciences, Sharif University of TechnologyTehran, Iran
Nezam Mahdavi-Amiri - Faculty of Mathematical Sciences, Sharif University of TechnologyTehran, Iran

We propose a time-varying dual accelerated gradient method for minimizing the average of n strongly convex and smooth functions over a time-varying network with n nodes. We prove that the time-varying dual accelerated gradient ascent method converges at a linear rate with the time to reach an ε-neighborhood of the solution being of O(ln ۱/ϵ). We test the proposed method on two classes of problems: L_۲-regularized least squares and logistic classification problems. For each class, we generate ۱۰۰۰ problems and use the Dolan-Moré performance profiles to compare our obtained results with the ones obtained by several state-of-the-art algorithms to illustrate the efficiency of our method.

Distributed Learning, Distributed Optimization, Time-Varying Networks