The problem of minimizing a sum of local convex objective functions over a networked system captures many important applications and has received much attention in the distributed optimization field. Most of existing work focuses on development of fast distributed algorithms under the presence of a central clock. The only known algorithms with convergence guarantees for this problem in asynchronous setup could achieve either sublinear rate under totally asynchronous setting or linear rate under partially asynchronous setting (with bounded delay). In this work, we built upon existing literature to develop and analyze an asynchronous Newton based approach for solving a penalized version of the problem. We show that this algorithm converges almost surely with global linear rate and local superlinear rate in expectation. Numerical studies confirm superior performance against other existing asynchronous methods.

One of the most important problems in the field of distributed optimization is the problem of minimizing a sum of local convex objective functions over a networked system. Most of the existing work in this area focus on developing distributed algorithms in a synchronous setting under the presence of a central clock, where the agents need to wait for the slowest one to finish the update, before proceeding to the next iterate. Asynchronous distributed algorithms remove the need for a central coordinator, reduce the synchronization wait, and allow some agents to compute faster and execute more iterations. In the asynchronous setting, the only known algorithms for solving this problem could achieve either linear or sublinear rate of convergence. In this work, we built upon the existing literature to develop and analyze an asynchronous Newton-based method to solve a penalized version of the problem. We show that this algorithm guarantees almost sure convergence with global linear and local quadratic rate in expectation.Numerical studies confirm superior performance of our algorithm against other asynchronous methods.

In this paper, we study the problem of minimizing a sum of convex objective functions, each of which is locally available to an agent in the network. Distributed optimization algorithms make it possible for the agents to cooperatively solve the problem through local computations and communications with neighbors. Lagrangian-based distributed optimization algorithms have received significant attention in recent years, due to their exact convergence property. However, many of these algorithms have slow convergence or are expensive to execute. In this paper, we develop a flexible framework of first-order primal-dual algorithms (FlexPD), which allows for multiple primal steps per iteration and can be customized for various applications with different computation and communication limitations. For strongly convex and Lipschitz gradient objective functions, we establish linear convergence of our proposed algorithms to the optimal solution. Simulation results confirm the superior performance of our algorithm compared to the existing methods.

No abstract

No abstract