English

Learning Complexity Dimensions for a Continuous-Time Control System

Optimization and Control 2007-05-23 v2 Machine Learning

Abstract

This paper takes a computational learning theory approach to a problem of linear systems identification. It is assumed that input signals have only a finite number k of frequency components, and systems to be identified have dimension no greater than n. The main result establishes that the sample complexity needed for identification scales polynomially with n and logarithmically with k.

Keywords

Cite

@article{arxiv.math/0012163,
  title  = {Learning Complexity Dimensions for a Continuous-Time Control System},
  author = {Pirkko Kuusela and Daniel Ocone and Eduardo D. Sontag},
  journal= {arXiv preprint arXiv:math/0012163},
  year   = {2007}
}

Comments

33 pages