Linear Convergence for Distributed Optimization Without Strong Convexity

This paper considers the distributed optimization problem of minimizing a global cost function formed by a sum of local smooth cost functions by using local information exchange. Various distributed optimization algorithms have been proposed for solving such a problem. A standard condition for proving the linear convergence for existing distributed algorithms is the strong convexity of the cost functions. However, the strong convexity may not hold for many practical applications, such as least squares and logistic regression. In this paper, we propose a distributed primal-dual gradient descent algorithm and establish its linear convergence under the condition that the global cost function satisfies the Polyak–Łojasiewicz condition. This condition is weaker than strong convexity and the global minimizer is not necessarily unique. The theoretical result is illustrated by numerical simulations.

[1]  K. Johansson,et al.  Exponential Convergence for Distributed Optimization Under the Restricted Secant Inequality Condition , 2019, IFAC-PapersOnLine.

[2]  John N. Tsitsiklis,et al.  Distributed Asynchronous Deterministic and Stochastic Gradient Optimization Algorithms , 1984, 1984 American Control Conference.

[3]  Ziyang Meng,et al.  A survey of distributed optimization , 2019, Annu. Rev. Control..

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

[5]  Magnus Egerstedt,et al.  Graph Theoretic Methods in Multiagent Networks , 2010, Princeton Series in Applied Mathematics.

[6]  Karl Henrik Johansson,et al.  Subgradient methods and consensus algorithms for solving convex optimization problems , 2008, 2008 47th IEEE Conference on Decision and Control.

[7]  John S. Baras,et al.  Performance Evaluation of the Consensus-Based Distributed Subgradient Method Under Random Communication Topologies , 2011, IEEE Journal of Selected Topics in Signal Processing.

[8]  Karl Henrik Johansson,et al.  Distributed Optimization for Second-Order Multi-Agent Systems with Dynamic Event-Triggered Communication , 2018, 2018 IEEE Conference on Decision and Control (CDC).

[9]  Ziyang Meng,et al.  A Distributed Algorithm for Economic Dispatch Over Time-Varying Directed Networks With Delays , 2017, IEEE Transactions on Industrial Electronics.

[10]  John N. Tsitsiklis,et al.  Parallel and distributed computation , 1989 .

[11]  F. Facchinei,et al.  Finite-Dimensional Variational Inequalities and Complementarity Problems , 2003 .

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

[13]  Sonia Martínez,et al.  Distributed convex optimization via continuous-time coordination algorithms with discrete-time communication , 2014, Autom..

[14]  Tao Yang,et al.  Accelerated Distributed Energy Management for Microgrids , 2018, 2018 IEEE Power & Energy Society General Meeting (PESGM).

[15]  Yurii Nesterov,et al.  Linear convergence of first order methods for non-strongly convex optimization , 2015, Math. Program..

[16]  Xinlei Yi,et al.  Distributed Finite-time Least Squares Solver for Network Linear Equations , 2018, 1810.00156.

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

[18]  Qing Ling,et al.  On the Convergence of Decentralized Gradient Descent , 2013, SIAM J. Optim..

[19]  Shu Liang,et al.  Exponential convergence of distributed primal-dual convex optimization algorithm without strong convexity , 2019, Autom..

[20]  Angelia Nedic,et al.  Convergence Rate of Distributed Averaging Dynamics and Optimization in Networks , 2015, Found. Trends Syst. Control..

[21]  John N. Tsitsiklis,et al.  Problems in decentralized decision making and computation , 1984 .

[22]  Mark W. Schmidt,et al.  Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition , 2016, ECML/PKDD.

[23]  Wei Shi,et al.  Geometrically convergent distributed optimization with uncoordinated step-sizes , 2016, 2017 American Control Conference (ACC).

[24]  Sonia Martínez,et al.  On Distributed Convex Optimization Under Inequality and Equality Constraints , 2010, IEEE Transactions on Automatic Control.

[25]  Na Li,et al.  Accelerated Distributed Nesterov Gradient Descent , 2017, IEEE Transactions on Automatic Control.

[26]  Hui Zhang,et al.  Restricted strong convexity and its applications to convergence analysis of gradient-type methods in convex optimization , 2015, Optim. Lett..

[27]  Na Li,et al.  Distributed Zero-Order Algorithms for Nonconvex Multi-Agent optimization , 2019, 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

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