Auto-tuning procedures for distributed nonparametric regression algorithms

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.