On the Influence of Informed Agents on Learning and Adaptation over Networks
arXiv:1203.1524 · doi:10.1109/TSP.2012.2230167
Abstract
Adaptive networks consist of a collection of agents with adaptation and learning abilities. The agents interact with each other on a local level and diffuse information across the network through their collaborations. In this work, we consider two types of agents: informed agents and uninformed agents. The former receive new data regularly and perform consultation and in-network tasks, while the latter do not collect data and only participate in the consultation tasks. We examine the performance of adaptive networks as a function of the proportion of informed agents and their distribution in space. The results reveal some interesting and surprising trade-offs between convergence rate and mean-square performance. In particular, among other results, it is shown that the performance of adaptive networks does not necessarily improve with a larger proportion of informed agents. Instead, it is established that the larger the proportion of informed agents is, the faster the convergence rate of the network becomes albeit at the expense of some deterioration in mean-square performance. The results further establish that uninformed agents play an important role in determining the steady-state performance of the network, and that it is preferable to keep some of the highly connected agents uninformed. The arguments reveal an important interplay among three factors: the number and distribution of informed agents in the network, the convergence rate of the learning process, and the estimation accuracy in steady-state. Expressions that quantify these relations are derived, and simulations are included to support the theoretical findings. We further apply the results to two models that are widely used to represent behavior over complex networks, namely, the Erdos-Renyi and scale-free models.
arXiv comment35 pages, 8 figures
References in corpus (12)
- Emergence of scaling in random networks
- Statistical mechanics of complex networks
- Gossip Algorithms for Distributed Signal Processing
- Diffusion Adaptation Strategies for Distributed Optimization and Learning over Networks
- Spectra of "Real-World" Graphs: Beyond the Semi-Circle Law
- Diffusion Strategies Outperform Consensus Strategies for Distributed Estimation over Adaptive Networks
- Distributed Learning in Wireless Sensor Networks
- Convergence Rate Analysis of Distributed Gossip (Linear Parameter) Estimation: Fundamental Limits and Tradeoffs
- Spectra and eigenvectors of scale-free networks
- Diffusion Adaptation over Networks under Imperfect Information Exchange and Non-stationary Data
- Performance Limits for Distributed Estimation Over LMS Adaptive Networks
- Higher Dimensional Consensus: Learning in Large-Scale Networks
Cited by in corpus (6)
- Distributed Random Projection Algorithm for Convex Optimization
- Distributed Decision-Making over Adaptive Networks
- Adaptive Diffusion Schemes for Heterogeneous Networks
- Single Bit and Reduced Dimension Diffusion Strategies Over Distributed Networks
- Distributed Gradient Methods with Variable Number of Working Nodes
- A Multitask Diffusion Strategy with Optimized Inter-Cluster Cooperation