Complexity of model classes and smoothing noisy data

Peter L. Bartlett, Sanjeev R. Kulkarni

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Scopus citations

Abstract

We consider the problem of smoothing a sequence of noisy observations using a fixed class of models. Via a deterministic analysis, we obtain necessary and sufficient conditions on the noise sequence and model class that ensure that a class of natural estimators gives near optimal smoothing. In the case of i.i.d. random noise, we show that the accuracy of these estimators depends on a measure of complexity of the model class involving covering numbers. Our formulation and results are quite general and are related to a number of problems in learning, prediction, and estimation. As a special case, we consider an application to output smoothing for certain classes of linear and nonlinear systems. The performance of output smoothing is given in terms of natural complexity parameters of the model class, such as bounds on the order of linear systems, the l 1-norm of the impulse response of stable linear systems, or the memory of a Lipschitz nonlinear system satisfying a fading memory condition.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Conference on Decision and Control
Editors Anon
Pages2312-2317
Number of pages6
Volume2
StatePublished - Dec 1 1996
Externally publishedYes
EventProceedings of the 35th IEEE Conference on Decision and Control. Part 4 (of 4) - Kobe, Jpn
Duration: Dec 11 1996Dec 13 1996

Other

OtherProceedings of the 35th IEEE Conference on Decision and Control. Part 4 (of 4)
CityKobe, Jpn
Period12/11/9612/13/96

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Safety, Risk, Reliability and Quality
  • Chemical Health and Safety

Fingerprint Dive into the research topics of 'Complexity of model classes and smoothing noisy data'. Together they form a unique fingerprint.

  • Cite this

    Bartlett, P. L., & Kulkarni, S. R. (1996). Complexity of model classes and smoothing noisy data. In Anon (Ed.), Proceedings of the IEEE Conference on Decision and Control (Vol. 2, pp. 2312-2317)