Learning Complexity Dimensions for a Continuous-Time Control System

Simple item page
dc.creatorKuusela, Pirkko
dc.creatorOcone, Daniel
dc.creatorSontag, Eduardo D.
dc.date2000-12-18
dc.date2000-12-19
dc.date.accessioned2026-07-07T04:39:16Z
dc.date.available2026-07-07T04:39:16Z
dc.descriptionThis 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.
dc.description33 pages
dc.identifierhttps://arxiv.org/abs/math/0012163
dc.identifierhttp://arxiv.org/abs/math/0012163
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/60592
dc.subjectOptimization and Control
dc.subjectMachine Learning
dc.subject93C05
dc.titleLearning Complexity Dimensions for a Continuous-Time Control System
dc.typetext

Files

Collections

arXiv