Abstract | ||
---|---|---|
We propose a distributed regression algorithm with the capability of automatically calibrating its parameters during its on-line functioning. The estimation procedure corresponds to a Regularization Network, i.e., the structural form of the estimator is a linear combination of basis functions which coefficients are computed by solving a linear system. The automatic tuning strategy instead constructs and then exploits opportune bounds on the distance between the distributed estimation results and the unknown centralized optimal estimate that would be computed processing the whole dataset at once. By numerical simulations we show how the proposed procedure allows the sensor networks to effectively self-tune the parameters of the distributed regression scheme by simple consensus strategies. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ECC.2015.7330614 | 2015 European Control Conference (ECC) |
Keywords | Field | DocType |
distributed regression,distributed calibration,self-organizing sensor networks,regularization networks,nonparametric estimation | Kernel (linear algebra),Linear combination,Mathematical optimization,Principal component regression,Linear system,Nonparametric regression,Polynomial regression,Algorithm,Basis function,Mathematics,Estimator | Conference |
Citations | PageRank | References |
0 | 0.34 | 10 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Damiano Varagnolo | 1 | 121 | 15.26 |
Pillonetto Gianluigi | 2 | 877 | 80.84 |
luca schenato | 3 | 22 | 1.42 |