A Canonical Form for First-Order Distributed Optimization Algorithms

We consider the distributed optimization problem in which a network of agents aims to minimize the average of local functions. To solve this problem, several algorithms have recently been proposed where agents perform various combinations of communication with neighbors, local gradient computations, and updates to local state variables. In this paper, we present a canonical form that characterizes any first-order distributed algorithm that can be implemented using a single round of communication and gradient computation per iteration, and where each agent stores up to two state variables. The canonical form features a minimal set of parameters that are both unique and expressive enough to capture any distributed algorithm in this class. The generic nature of our canonical form enables the systematic analysis and design of distributed optimization algorithms.

[1]  Wei Shi,et al.  Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs , 2016, SIAM J. Optim..

[2]  Dusan Jakovetic,et al.  A Unification and Generalization of Exact Distributed First-Order Methods , 2017, IEEE Transactions on Signal and Information Processing over Networks.

[3]  Bin Hu,et al.  Robust convergence analysis of distributed optimization algorithms , 2017, 2017 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[4]  Lihua Xie,et al.  Augmented distributed gradient methods for multi-agent optimization under uncoordinated constant stepsizes , 2015, 2015 54th IEEE Conference on Decision and Control (CDC).

[5]  H. Vincent Poor,et al.  A Collaborative Training Algorithm for Distributed Learning , 2009, IEEE Transactions on Information Theory.

[6]  Wei Shi,et al.  A Decentralized Proximal-Gradient Method With Network Independent Step-Sizes and Separated Convergence Rates , 2017, IEEE Transactions on Signal Processing.

[7]  Dusan Jakovetic,et al.  A Unification, Generalization, and Acceleration of Exact Distributed First Order Methods , 2017, ArXiv.

[8]  Qing Ling,et al.  Decentralized Sparse Signal Recovery for Compressive Sleeping Wireless Sensor Networks , 2010, IEEE Transactions on Signal Processing.

[9]  R A Freeman,et al.  A complete characterization of a class of robust linear average consensus protocols , 2010, Proceedings of the 2010 American Control Conference.

[10]  R. Roesser.  A discrete state-space model for linear image processing , 1975 .

[11]  Benjamin Recht,et al.  Analysis and Design of Optimization Algorithms via Integral Quadratic Constraints , 2014, SIAM J. Optim..

[12]  Björn Johansson,et al.  On Distributed Optimization in Networked Systems , 2008 .

[13]  Usman A. Khan,et al.  Distributed Heavy-Ball: A Generalization and Acceleration of First-Order Methods With Gradient Tracking , 2018, IEEE Transactions on Automatic Control.

[14]  Ettore Fornasini,et al.  Doubly-indexed dynamical systems: State-space models and structural properties , 1978, Mathematical systems theory.

[15]  Angelia Nedic,et al.  A Distributed Stochastic Gradient Tracking Method , 2018, 2018 IEEE Conference on Decision and Control (CDC).

[16]  Michael I. Jordan,et al.  A General Analysis of the Convergence of ADMM , 2015, ICML.

[17]  Ali H. Sayed,et al.  Exact Diffusion for Distributed Optimization and Learning—Part I: Algorithm Development , 2017, IEEE Transactions on Signal Processing.

[18]  Qing Ling,et al.  EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization , 2014, 1404.6264.

[19]  Qing Ling,et al.  A Proximal Gradient Algorithm for Decentralized Composite Optimization , 2015, IEEE Transactions on Signal Processing.

[20]  Na Li,et al.  Harnessing smoothness to accelerate distributed optimization , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

[21]  Ali H. Sayed,et al.  Exact Diffusion for Distributed Optimization and Learning—Part II: Convergence Analysis , 2017, IEEE Transactions on Signal Processing.

[22]  Angelia Nedic,et al.  Distributed stochastic gradient tracking methods , 2018, Mathematical Programming.

[23]  Lihua Xie,et al.  Convergence of Asynchronous Distributed Gradient Methods Over Stochastic Networks , 2018, IEEE Transactions on Automatic Control.

[24]  Na Li,et al.  Accelerated Distributed Nesterov Gradient Descent for smooth and strongly convex functions , 2016, 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[25]  Asuman E. Ozdaglar,et al.  Distributed Subgradient Methods for Multi-Agent Optimization , 2009, IEEE Transactions on Automatic Control.