Regularized Primal–Dual Subgradient Method for Distributed Constrained Optimization

In this paper, we study the distributed constrained optimization problem where the objective function is the sum of local convex cost functions of distributed nodes in a network, subject to a global inequality constraint. To solve this problem, we propose a consensus-based distributed regularized primal-dual subgradient method. In contrast to the existing methods, most of which require projecting the estimates onto the constraint set at every iteration, only one projection at the last iteration is needed for our proposed method. We establish the convergence of the method by showing that it achieves an O(K-1/4) convergence rate for general distributed constrained optimization, where K is the iteration counter. Finally, a numerical example is provided to validate the convergence of the propose method.

[1]  Choon Yik Tang,et al.  Gossip Algorithms for Convex Consensus Optimization Over Networks , 2010, IEEE Transactions on Automatic Control.

[2]  Wei Ren,et al.  Constrained Consensus in Unbalanced Networks With Communication Delays , 2014, IEEE Transactions on Automatic Control.

[3]  Daniel W. C. Ho,et al.  Fault-Tolerant Consensus of Multi-Agent System With Distributed Adaptive Protocol , 2015, IEEE Transactions on Cybernetics.

[4]  Ιωαννησ Τσιτσικλησ,et al.  PROBLEMS IN DECENTRALIZED DECISION MAKING AND COMPUTATION , 1984 .

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

[6]  Sonia Martínez,et al.  An Approximate Dual Subgradient Algorithm for Multi-Agent Non-Convex Optimization , 2010, IEEE Transactions on Automatic Control.

[7]  Randal W. Beard,et al.  Consensus seeking in multiagent systems under dynamically changing interaction topologies , 2005, IEEE Transactions on Automatic Control.

[8]  Kevin L. Moore,et al.  Studies on Resilient Control Through Multiagent Consensus Networks Subject to Disturbances , 2014, IEEE Transactions on Cybernetics.

[9]  Stephen P. Boyd,et al.  Fast linear iterations for distributed averaging , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

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

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

[12]  John N. Tsitsiklis,et al.  Distributed subgradient methods and quantization effects , 2008, 2008 47th IEEE Conference on Decision and Control.

[13]  Tingwen Huang,et al.  Cooperative Distributed Optimization in Multiagent Networks With Delays , 2015, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[14]  Wenwu Yu,et al.  An Overview of Recent Progress in the Study of Distributed Multi-Agent Coordination , 2012, IEEE Transactions on Industrial Informatics.

[15]  Daniel W. C. Ho,et al.  Randomized Gradient-Free Method for Multiagent Optimization Over Time-Varying Networks , 2015, IEEE Transactions on Neural Networks and Learning Systems.

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

[17]  Jürgen Kurths,et al.  Consensus over directed static networks with arbitrary finite communication delays. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

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

[19]  Deming Yuan,et al.  Distributed Primal-Dual Subgradient Method for Multiagent Optimization via Consensus Algorithms. , 2011, IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society.

[20]  Karl Henrik Johansson,et al.  Approximate Projected Consensus for Convex Intersection Computation: Convergence Analysis and Critical Error Angle , 2014, IEEE Transactions on Automatic Control.

[21]  Yoram Singer,et al.  Efficient projections onto the l1-ball for learning in high dimensions , 2008, ICML '08.

[22]  Ali H. Sayed,et al.  Diffusion Adaptation Strategies for Distributed Optimization and Learning Over Networks , 2011, IEEE Transactions on Signal Processing.

[23]  Anna Scaglione,et al.  Distributed Constrained Optimization by Consensus-Based Primal-Dual Perturbation Method , 2013, IEEE Transactions on Automatic Control.

[24]  Stephen P. Boyd,et al.  Randomized gossip algorithms , 2006, IEEE Transactions on Information Theory.

[25]  Gang Feng,et al.  Consensus of Linear Multi-Agent Systems by Distributed Event-Triggered Strategy , 2016, IEEE Transactions on Cybernetics.

[26]  Jinfeng Yi,et al.  Stochastic Gradient Descent with Only One Projection , 2012, NIPS.

[27]  Yiguang Hong,et al.  Quantized Subgradient Algorithm and Data-Rate Analysis for Distributed Optimization , 2014, IEEE Transactions on Control of Network Systems.

[28]  José M. F. Moura,et al.  Fast Distributed Gradient Methods , 2011, IEEE Transactions on Automatic Control.

[29]  Jie Lin,et al.  Coordination of groups of mobile autonomous agents using nearest neighbor rules , 2003, IEEE Trans. Autom. Control..

[30]  Daniel W. C. Ho,et al.  Globally Exponential Synchronization and Synchronizability for General Dynamical Networks , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

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

[32]  Richard M. Murray,et al.  Consensus problems in networks of agents with switching topology and time-delays , 2004, IEEE Transactions on Automatic Control.

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