Exponential convergence of distributed primal-dual convex optimization algorithm without strong convexity

Abstract This paper establishes exponential convergence rates for a class of primal–dual gradient algorithms in distributed optimization without strong convexity. The convergence analysis is based on a carefully constructed Lyapunov function. By evaluating metric subregularity of the primal–dual gradient map, we present a general criterion under which the algorithm achieves exponential convergence. To facilitate practical applications of this criterion, several simplified sufficient conditions are derived. We also prove that although these results are developed for the continuous-time algorithms, they carry over in a parallel manner to the discrete-time algorithms constructed by using Euler’s approximation method.

[1]  Yiguang Hong,et al.  Distributed Continuous-Time Algorithm for Constrained Convex Optimizations via Nonsmooth Analysis Approach , 2015, IEEE Transactions on Automatic Control.

[2]  Andre Wibisono,et al.  A variational perspective on accelerated methods in optimization , 2016, Proceedings of the National Academy of Sciences.

[3]  Shu Liang,et al.  Distributed Continuous-Time Algorithms for Resource Allocation Problems Over Weight-Balanced Digraphs , 2018, IEEE Transactions on Cybernetics.

[4]  Qingshan Liu,et al.  A Collective Neurodynamic Approach to Distributed Constrained Optimization , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[5]  Dimitri P. Bertsekas,et al.  Incremental proximal methods for large scale convex optimization , 2011, Math. Program..

[6]  Lennart Ljung,et al.  Analysis of recursive stochastic algorithms , 1977 .

[7]  Lihua Xie,et al.  Distributed constrained optimal consensus of multi-agent systems , 2016, Autom..

[8]  Brian D. O. Anderson,et al.  Network Flows That Solve Linear Equations , 2015, IEEE Transactions on Automatic Control.

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

[10]  Qing Ling,et al.  On the Linear Convergence of the ADMM in Decentralized Consensus Optimization , 2013, IEEE Transactions on Signal Processing.

[11]  Asuman E. Ozdaglar,et al.  Convergence Rate of Distributed ADMM Over Networks , 2016, IEEE Transactions on Automatic Control.

[12]  Yiguang Hong,et al.  Distributed optimal coordination for multiple heterogeneous Euler-Lagrangian systems , 2017, Autom..

[13]  Yiguang Hong,et al.  Distributed regression estimation with incomplete data in multi-agent networks , 2018, Science China Information Sciences.

[14]  Shengyuan Xu,et al.  Zeroth-Order Method for Distributed Optimization With Approximate Projections , 2016, IEEE Transactions on Neural Networks and Learning Systems.

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

[16]  Asuman E. Ozdaglar,et al.  Approximate Primal Solutions and Rate Analysis for Dual Subgradient Methods , 2008, SIAM J. Optim..

[17]  Ion Necoara,et al.  On linear convergence of a distributed dual gradient algorithm for linearly constrained separable convex problems , 2014, Autom..

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

[19]  Mauro Forti,et al.  Generalized neural network for nonsmooth nonlinear programming problems , 2004, IEEE Transactions on Circuits and Systems I: Regular Papers.

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

[21]  Shu Liang,et al.  Distributed Nash equilibrium seeking for aggregative games with coupled constraints , 2016, Autom..

[22]  R. Brockett,et al.  Dynamical systems that sort lists, diagonalize matrices and solve linear programming problems , 1988, Proceedings of the 27th IEEE Conference on Decision and Control.

[23]  Jing Wang,et al.  A control perspective for centralized and distributed convex optimization , 2011, IEEE Conference on Decision and Control and European Control Conference.

[24]  Bahman Gharesifard,et al.  Distributed Continuous-Time Convex Optimization on Weight-Balanced Digraphs , 2012, IEEE Transactions on Automatic Control.

[25]  Feng Liu,et al.  Initialization-free distributed algorithms for optimal resource allocation with feasibility constraints and application to economic dispatch of power systems , 2015, Autom..

[26]  Shouyang Wang,et al.  Distributed continuous-time approximate projection protocols for shortest distance optimization problems , 2015, Autom..

[27]  Jorge Cortés,et al.  Noise-to-state exponentially stable distributed convex optimization on weight-balanced digraphs , 2013, 52nd IEEE Conference on Decision and Control.

[28]  Ashish Cherukuri,et al.  Initialization-free distributed coordination for economic dispatch under varying loads and generator commitment , 2014, Autom..

[29]  B. V. Dean,et al.  Studies in Linear and Non-Linear Programming. , 1959 .

[30]  Qingshan Liu,et al.  A Multi-Agent System With a Proportional-Integral Protocol for Distributed Constrained Optimization , 2017, IEEE Transactions on Automatic Control.

[31]  Fernando Paganini,et al.  Stability of primal-dual gradient dynamics and applications to network optimization , 2010, Autom..

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