Distributed linear parameter estimation: asymptotically efficient adaptive strategies
From MaRDI portal
adaptive algorithmsasymptotically efficientdistributed estimationmixed time-scalemultiagent systemsstochastic approximation
Signal detection and filtering (aspects of stochastic processes) (60G35) Markov processes: estimation; hidden Markov models (62M05) Non-Markovian processes: estimation (62M09) Agent technology and artificial intelligence (68T42) Estimation and detection in stochastic control theory (93E10) Stochastic learning and adaptive control (93E35) Detection theory in information and communication theory (94A13)
Abstract: The paper considers the problem of distributed adaptive linear parameter estimation in multi-agent inference networks. Local sensing model information is only partially available at the agents and inter-agent communication is assumed to be unpredictable. The paper develops a generic mixed time-scale stochastic procedure consisting of simultaneous distributed learning and estimation, in which the agents adaptively assess their relative observation quality over time and fuse the innovations accordingly. Under rather weak assumptions on the statistical model and the inter-agent communication, it is shown that, by properly tuning the consensus potential with respect to the innovation potential, the asymptotic information rate loss incurred in the learning process may be made negligible. As such, it is shown that the agent estimates are asymptotically efficient, in that their asymptotic covariance coincides with that of a centralized estimator (the inverse of the centralized Fisher information rate for Gaussian systems) with perfect global model information and having access to all observations at all times. The proof techniques are mainly based on convergence arguments for non-Markovian mixed time scale stochastic approximation procedures. Several approximation results developed in the process are of independent interest.
Recommendations
- Adaptive Distributed Estimation Based on Recursive Least-Squares and Partial Diffusion
- Distributed nonlinear estimation: a recursive optimization approach
- On Distributed Linear Estimation With Observation Model Uncertainties
- Distributed linear estimation over sensor networks
- Distributed adaptive estimation with probabilistic data association
- Distributed function estimation: adaptation using minimal communication
- Distributed Estimation of a Parametric Field: Algorithms and Performance Analysis
- Diffusion recursive least-squares for distributed estimation over adaptive networks
- Distributed and Recursive Parameter Estimation in Parametrized Linear State-Space Models
- Robust Distributed Estimation for Linear Systems Under Intermittent Information
Cited in
(24)- Generalization of a result of Fabian on the asymptotic normality of stochastic approximation
- Differentially private distributed parameter estimation
- Adaptation, learning, and optimization over networks
- Resilient distributed field estimation
- Adaptive clustering based on element-wised distance for distributed estimation over multi-task networks
- Stochastic approximation based consensus dynamics over Markovian networks
- Distributed parametric and nonparametric regression with on-line performance bounds computation
- A note on distributed estimation and sufficiency
- Convergence analysis of distributed inference with vector-valued Gaussian belief propagation
- Performance Limits for Distributed Estimation Over LMS Adaptive Networks
- Asymptotically Optimum Distributed Estimation in the Presence of Attacks
- Efficient distributed sensing using adaptive censoring-based inference
- Analysis of normalized least mean squares-based consensus adaptive filters under a general information condition
- Distributed and Recursive Parameter Estimation in Parametrized Linear State-Space Models
- Event-triggered distributed estimation with decaying communication rate
- Distributed Linear Estimation Via a Roaming Token
- Differentially private resilient distributed cooperative online estimation over digraphs
- Distributed event-triggered unadjusted Langevin algorithm for Bayesian learning
- Nonlinear Consensus+Innovations under Correlated Heavy-Tailed Noises: Mean Square Convergence Rate and Asymptotics
- Secured filters based on saturated innovations
- Distributed Recursive Estimation under Heavy-Tail Communication Noise
- Distributed adaptive estimation without persistence of excitation: an online optimization perspective
- Privacy-preserving distributed adaptive estimation for non-stationary regression data
- Signal-comparison-based distributed estimation under decaying average data rate communications
This page was built for publication: Distributed linear parameter estimation: asymptotically efficient adaptive strategies
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2848581)
