Tight Linear Convergence Rate of ADMM for Decentralized Optimization

The present paper considers leveraging network topology information to improve the convergence rate of ADMM for decentralized optimization, where networked nodes work collaboratively to minimize the objective. Such problems can be solved efficiently using ADMM via decomposing the objective into easier subproblems. Properly exploiting network topology can significantly improve the algorithm performance. Hybrid ADMM explores the direction of exploiting node information by taking into account node centrality but fails to utilize edge information. This paper fills the gap by incorporating both node and edge information and provides a novel convergence rate bound for decentralized ADMM that explicitly depends on network topology. Such a novel bound is attainable for certain class of problems, thus tight. The explicit dependence further suggests possible directions to optimal design of edge weights to achieve the best performance. Numerical experiments show that simple heuristic methods could achieve better performance, and also exhibits robustness to topology changes.

[1]  Qing Ling,et al.  Decentralized learning for wireless communications and networking , 2015, ArXiv.

[2]  Wotao Yin,et al.  On the Global and Linear Convergence of the Generalized Alternating Direction Method of Multipliers , 2016, J. Sci. Comput..

[3]  Euhanna Ghadimi,et al.  The ADMM algorithm for distributed averaging: Convergence rates and optimal parameter selection , 2014, 2014 48th Asilomar Conference on Signals, Systems and Computers.

[4]  Jonathan Eckstein Splitting methods for monotone operators with applications to parallel optimization , 1989 .

[5]  Robert Nowak,et al.  Distributed optimization in sensor networks , 2004, Third International Symposium on Information Processing in Sensor Networks, 2004. IPSN 2004.

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

[7]  Asuman E. Ozdaglar,et al.  Constrained Consensus and Optimization in Multi-Agent Networks , 2008, IEEE Transactions on Automatic Control.

[8]  Soummya Kar,et al.  Gossip Algorithms for Distributed Signal Processing , 2010, Proceedings of the IEEE.

[9]  G. Francca,et al.  How is Distributed ADMM Affected by Network Topology , 2017, 1710.00889.

[10]  Ioannis D. Schizas,et al.  Distributed Recursive Least-Squares for Consensus-Based In-Network Adaptive Estimation , 2009, IEEE Transactions on Signal Processing.

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

[12]  B. Mercier,et al.  A dual algorithm for the solution of nonlinear variational problems via finite element approximation , 1976 .

[13]  Angelia Nedic,et al.  Distributed Stochastic Subgradient Projection Algorithms for Convex Optimization , 2008, J. Optim. Theory Appl..

[14]  Reza Olfati-Saber,et al.  Consensus and Cooperation in Networked Multi-Agent Systems , 2007, Proceedings of the IEEE.

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

[16]  Georgios B. Giannakis,et al.  Hybrid ADMM: a unifying and fast approach to decentralized optimization , 2018, EURASIP J. Adv. Signal Process..

[17]  Heinz H. Bauschke,et al.  Convex Analysis and Monotone Operator Theory in Hilbert Spaces , 2011, CMS Books in Mathematics.

[18]  Ali Sayed,et al.  Adaptation, Learning, and Optimization over Networks , 2014, Found. Trends Mach. Learn..

[19]  Stephen P. Boyd,et al.  A Primer on Monotone Operator Methods , 2015 .

[20]  R. Glowinski,et al.  Sur l'approximation, par éléments finis d'ordre un, et la résolution, par pénalisation-dualité d'une classe de problèmes de Dirichlet non linéaires , 1975 .

[21]  R. Rockafellar Monotone Operators and the Proximal Point Algorithm , 1976 .

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

[23]  Marianna Bolla,et al.  Spectra, Euclidean representations and clusterings of hypergraphs , 1993, Discret. Math..

[24]  P. Lions,et al.  Splitting Algorithms for the Sum of Two Nonlinear Operators , 1979 .

[25]  D. Gabay Applications of the method of multipliers to variational inequalities , 1983 .

[26]  Qing Ling,et al.  Weighted ADMM for Fast Decentralized Network Optimization , 2016, IEEE Transactions on Signal Processing.

[27]  Georgios B. Giannakis,et al.  Graph-aware Weighted Hybrid ADMM for Fast Decentralized Optimization , 2018, 2018 52nd Asilomar Conference on Signals, Systems, and Computers.

[28]  Pascal Bianchi,et al.  Explicit Convergence Rate of a Distributed Alternating Direction Method of Multipliers , 2013, IEEE Transactions on Automatic Control.

[29]  U. Brandes A faster algorithm for betweenness centrality , 2001 .

[30]  H. H. Rachford,et al.  On the numerical solution of heat conduction problems in two and three space variables , 1956 .

[31]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[32]  Wei Ren,et al.  Information consensus in multivehicle cooperative control , 2007, IEEE Control Systems.

[33]  Shiqian Ma,et al.  On the Global Linear Convergence of the ADMM with MultiBlock Variables , 2014, SIAM J. Optim..

[34]  Alejandro Ribeiro,et al.  Consensus in Ad Hoc WSNs With Noisy Links—Part I: Distributed Estimation of Deterministic Signals , 2008, IEEE Transactions on Signal Processing.

[35]  Dimitri P. Bertsekas,et al.  On the Douglas—Rachford splitting method and the proximal point algorithm for maximal monotone operators , 1992, Math. Program..

[36]  Zhi-Quan Luo,et al.  On the linear convergence of the alternating direction method of multipliers , 2012, Mathematical Programming.

[37]  Martin J. Wainwright,et al.  Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling , 2010, IEEE Transactions on Automatic Control.