Learning dynamical systems in a stationary environment Academic Article

abstract

• We consider the problem of learning the input-output relation of a dynamical system from noisy data. Our method rests on the use of a smooth simultaneous estimator which generalizes the standard empirical estimator. In a stationary environment, our algorithm is shown to select a model which exhibits the Probably Approximately Correct (PAC) property under very mild conditions. This contribution should be thought of as a first attempt to extend concepts developed in learning theory to the field of system identification where, due to the presence of the system dynamics, the typical i.i.d. assumption on the data made in learning theory is not satisfied. 1998 Elsevier Science B.V. All rights reserved.

authors

• Kumar, Panganamala

published proceedings

• Systems & Control Letters

author list (cited authors)

• Campi, M. C., & Kumar, P. R.

citation count

• 28

complete list of authors

• Campi, MC||Kumar, PR

publication date

• June 1998

publisher

• Elsevier  Publisher

published in

• Systems & Control Letters  Journal

Digital Object Identifier (DOI)

• 10.1016/s0167-6911(98)00005-x

start page

• 125

end page

• 132

volume

• 34

issue

• 3

URL

• http://dx.doi.org/10.1016/s0167-6911(98)00005-x