Distributed subgradient methods and quantization effects

We consider a convex unconstrained optimization problem that arises in a network of agents whose goal is to cooperatively optimize the sum of the individual agent objective functions through local computations and communications. For this problem, we use averaging algorithms to develop distributed subgradient methods that can operate over a time-varying topology. Our focus is on the convergence rate of these methods and the degradation in performance when only quantized information is available. Based on our recent results on the convergence time of distributed averaging algorithms, we derive improved upper bounds on the convergence rate of the unquantized subgradient method. We then propose a distributed subgradient method under the additional constraint that agents can only store and communicate quantized information, and we provide bounds on its convergence rate that highlight the dependence on the number of quantization levels.

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

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

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

[4]  J. Hiriart-Urruty,et al.  Convex analysis and minimization algorithms , 1993 .

[5]  Vicsek,et al.  Novel type of phase transition in a system of self-driven particles. , 1995, Physical review letters.

[6]  Frank Kelly,et al.  Rate control for communication networks: shadow prices, proportional fairness and stability , 1998, J. Oper. Res. Soc..

[7]  Steven H. Low,et al.  Optimization flow control—I: basic algorithm and convergence , 1999, TNET.

[8]  Rayadurgam Srikant,et al.  The Mathematics of Internet Congestion Control , 2003 .

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

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

[11]  M. Cao,et al.  A Lower Bound on Convergence of a Distributed Network Consensus Algorithm , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[12]  Derong Liu.  The Mathematics of Internet Congestion Control , 2005, IEEE Transactions on Automatic Control.

[13]  Stephen P. Boyd,et al.  Gossip algorithms: design, analysis and applications , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[14]  Stephen P. Boyd,et al.  A space-time diffusion scheme for peer-to-peer least-squares estimation , 2006, 2006 5th International Conference on Information Processing in Sensor Networks.

[15]  J.N. Tsitsiklis,et al.  Convergence Rates in Distributed Consensus and Averaging , 2006, Proceedings of the 45th IEEE Conference on Decision and Control.

[16]  F. Fagnani,et al.  Communication constraints in coordinated consensus problems , 2006, 2006 American Control Conference.

[17]  A. Banerjee.  Convex Analysis and Optimization , 2006 .

[18]  R. Srikant,et al.  Quantized Consensus , 2006, 2006 IEEE International Symposium on Information Theory.

[19]  R. Carli,et al.  Average consensus on networks with transmission noise or quantization , 2007, 2007 European Control Conference (ECC).

[20]  A. Nedić,et al.  Stochastic Incremental Gradient Descent for Estimation in Sensor Networks , 2007, 2007 Conference Record of the Forty-First Asilomar Conference on Signals, Systems and Computers.

[21]  Angelia Nedic,et al.  On the rate of convergence of distributed subgradient methods for multi-agent optimization , 2007, 2007 46th IEEE Conference on Decision and Control.

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

[23]  John N. Tsitsiklis,et al.  Convergence Speed in Distributed Consensus and Averaging , 2009, SIAM J. Control. Optim..

[24]  John N. Tsitsiklis,et al.  On distributed averaging algorithms and quantization effects , 2007, 2008 47th IEEE Conference on Decision and Control.

[25]  K. Schittkowski,et al.  NONLINEAR PROGRAMMING , 2022 .