Stability and Performance Limits of Adaptive Primal-Dual Networks
Authors:
Preprint
Abstract
This work studies distributed primal-dual strategies for adaptation and learning over networks from streaming data. Two first-order methods are considered based on the Arrow-Hurwicz (AH) and augmented Lagrangian (AL) techniques. Several revealing results are discovered in relation to the performance and stability of these strategies when employed over adaptive networks. The conclusions establish that the advantages that these methods have for deterministic optimization problems do not necessarily carry over to stochastic optimization problems. It is found that they have narrower stability ranges and worse steady-state mean-square-error performance than primal methods of the consensus and diffusion type. It is also found that the AH technique can become unstable under a partial observation model, while the other techniques are able to recover the unknown under this scenario. A method to enhance the performance of AL strategies is proposed by tying the selection of the step-size to their regularization parameter. It is shown that this method allows the AL algorithm to approach the performance of consensus and diffusion strategies but that it remains less stable than these other strategies.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Distributed Energy-Aware Diffusion Least Mean Squares: Game-Theoretic LearningIEEE Journal of Selected Topics in Signal Processing, 2013
- Diffusion strategies for adaptation and learning over networks: an examination of distributed strategies and network behaviorIEEE Signal Processing Magazine, 2013
- Distributed computation of the Fiedler vector with application to topology inference in ad hoc networksSignal Processing, 2012
- Convergence Rate Analysis of Distributed Gossip (Linear Parameter) Estimation: Fundamental Limits and TradeoffsIEEE Journal of Selected Topics in Signal Processing, 2011
- Adaptive Learning in a World of ProjectionsIEEE Signal Processing Magazine, 2010
- Distributed Stochastic Subgradient Projection Algorithms for Convex OptimizationJournal of Optimization Theory and Applications, 2010
- Distributed Subgradient Methods for Multi-Agent OptimizationIEEE Transactions on Automatic Control, 2009
- A new incremental affine projection-based adaptive algorithm for distributed networksSignal Processing, 2008
- Parallel algorithms for variational inequalities over the Cartesian product of the intersections of the fixed point sets of nonexpansive mappingsJournal of Approximation Theory, 2008
- Quantized incremental algorithms for distributed optimizationIEEE Journal on Selected Areas in Communications, 2005