Distributed Pareto Optimization via Diffusion Strategies

We consider solving multi-objective optimization problems in a distributed manner by a network of cooperating and learning agents. The problem is equivalent to optimizing a global cost that is the sum of individual components. The optimizers of the individual components do not necessarily coincide and the network therefore needs to seek Pareto optimal solutions. We develop a distributed solution that relies on a general class of adaptive diffusion strategies. We show how the diffusion process can be represented as the cascade composition of three operators: two combination operators and a gradient descent operator. Using the Banach fixed-point theorem, we establish the existence of a unique fixed point for the composite cascade. We then study how close each agent converges towards this fixed point, and also examine how close the Pareto solution is to the fixed point. We perform a detailed mean-square error analysis and establish that all agents are able to converge to the same Pareto optimal solution within a sufficiently small mean-square-error (MSE) bound even for constant step-sizes. We illustrate one application of the theory to collaborative decision making in finance by a network of agents.

[1]  Tom M. Apostol,et al.  Book Reviews: Mathematical Analysis. A Modern Approach to Advanced Calculus , 1958 .

[2]  W. K. Hastings,et al.  Monte Carlo Sampling Methods Using Markov Chains and Their Applications , 1970 .

[3]  Richard M. Karp,et al.  Reducibility among combinatorial problems" in complexity of computer computations , 1972 .

[4]  E. Kreyszig.  Introductory Functional Analysis With Applications , 1978 .

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

[6]  Charles R. Johnson,et al.  Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[7]  D. Ruppert,et al.  Efficient Estimations from a Slowly Convergent Robbins-Monro Process , 1988 .

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

[9]  Boris Polyak,et al.  Acceleration of stochastic approximation by averaging , 1992 .

[10]  O. Nelles,et al.  An Introduction to Optimization , 1996, IEEE Antennas and Propagation Magazine.

[11]  Dimitri P. Bertsekas,et al.  A New Class of Incremental Gradient Methods for Least Squares Problems , 1997, SIAM J. Optim..

[12]  D. Bertsekas,et al.  Convergen e Rate of In remental Subgradient Algorithms , 2000 .

[13]  Dimitri P. Bertsekas,et al.  Incremental Subgradient Methods for Nondifferentiable Optimization , 2001, SIAM J. Optim..

[14]  M. Rubinstein..  Markowitz's "Portfolio Selection": A Fifty-Year Retrospective , 2002 .

[15]  Alan J. Laub,et al.  Matrix analysis - for scientists and engineers , 2004 .

[16]  Stephen P. Boyd,et al.  Fastest Mixing Markov Chain on a Graph , 2004, SIAM Rev..

[17]  Robert D. Nowak,et al.  Quantized incremental algorithms for distributed optimization , 2005, IEEE Journal on Selected Areas in Communications.

[18]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[19]  Daniel Pérez Palomar,et al.  A tutorial on decomposition methods for network utility maximization , 2006, IEEE Journal on Selected Areas in Communications.

[20]  Ali H. Sayed,et al.  Incremental Adaptive Strategies Over Distributed Networks , 2007, IEEE Transactions on Signal Processing.

[21]  S. Barbarossa,et al.  Bio-Inspired Sensor Network Design , 2007, IEEE Signal Processing Magazine.

[22]  Jonathon A. Chambers,et al.  A new incremental affine projection-based adaptive algorithm for distributed networks , 2008, Signal Process..

[23]  Minghua Chen,et al.  Utility maximization in peer-to-peer systems , 2008, SIGMETRICS '08.

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

[25]  A. Fitt.  Markowitz portfolio theory for soccer spread betting , 2008 .

[26]  Ali H. Sayed,et al.  Adaptive Filters , 2008 .

[27]  Ali H. Sayed,et al.  Diffusion Least-Mean Squares Over Adaptive Networks: Formulation and Performance Analysis , 2008, IEEE Transactions on Signal Processing.

[28]  Ling Guan,et al.  Distributed Throughput Maximization in P2P VoD Applications , 2009, IEEE Transactions on Multimedia.

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

[30]  Ali H. Sayed,et al.  Diffusion LMS Strategies for Distributed Estimation , 2010, IEEE Transactions on Signal Processing.

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

[32]  Behrouz Touri,et al.  Asynchronous stochastic convex optimization over random networks: Error bounds , 2010, 2010 Information Theory and Applications Workshop (ITA).

[33]  Isao Yamada,et al.  Link probability control for probabilistic diffusion least-mean squares over resource-constrained networks , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[34]  Christopher R. Blake,et al.  Chapter 14 Applications of Markowitz Portfolio Theory To Pension Fund Design , 2010 .

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

[36]  Soummya Kar,et al.  Convergence Rate Analysis of Distributed Gossip (Linear Parameter) Estimation: Fundamental Limits and Tradeoffs , 2010, IEEE Journal of Selected Topics in Signal Processing.

[37]  Ali H. Sayed,et al.  Mobile Adaptive Networks , 2011, IEEE Journal of Selected Topics in Signal Processing.

[38]  Sergio Barbarossa,et al.  A Bio-Inspired Swarming Algorithm for Decentralized Access in Cognitive Radio , 2011, IEEE Transactions on Signal Processing.

[39]  Ali H. Sayed,et al.  Bio-inspired swarming for dynamic radio access based on diffusion adaptation , 2011, 2011 19th European Signal Processing Conference.

[40]  Sergios Theodoridis,et al.  Adaptive Robust Distributed Learning in Diffusion Sensor Networks , 2011, IEEE Transactions on Signal Processing.

[41]  Sergios Theodoridis,et al.  Adaptive Learning in a World of Projections , 2011, IEEE Signal Processing Magazine.

[42]  Angelia Nedic,et al.  Distributed Asynchronous Constrained Stochastic Optimization , 2011, IEEE Journal of Selected Topics in Signal Processing.

[43]  Usman A. Khan,et al.  Networked estimation under information constraints , 2011, ArXiv.

[44]  Ali H. Sayed,et al.  On the limiting behavior of distributed optimization strategies , 2012, 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

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

[46]  Ali H. Sayed,et al.  Diffusion Adaptation over Networks , 2012, ArXiv.

[47]  Ali H. Sayed,et al.  Performance Limits for Distributed Estimation Over LMS Adaptive Networks , 2012, IEEE Transactions on Signal Processing.

[48]  Ali H. Sayed,et al.  Distributed throughput optimization over P2P mesh networks using diffusion adaptation , 2012, 2012 IEEE International Conference on Communications (ICC).

[49]  Ali H. Sayed,et al.  Distributed pareto-optimal solutions via diffusion adaptation , 2012, 2012 IEEE Statistical Signal Processing Workshop (SSP).