Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Improved Sample Complexity Estimates for Statistical Learning Control of Uncertain Systems
 

Summary: Improved Sample Complexity Estimates for Statistical Learning
Control of Uncertain Systems
V. Koltchinskii
, C. T. Abdallah
, M. Ariola
, P. Dorato§
, D. Panchenko¶
Abstract
Recently, probabilistic methods and statistical learning theory have been shown to provide approximate
solutions to "difficult" control problems. Unfortunately, the number of samples required in order to
guarantee stringent performance levels may be prohibitively large. This paper introduces bootstrap
learning methods and the concept of stopping times to drastically reduce the bound on the number of
samples required to achieve a performance level. We then apply these results to obtain more efficient
algorithms which probabilistically guarantee stability and robustness levels when designing controllers
for uncertain systems.
keywords: Statistical Learning, Radamacher bootstrap, Robust Control, Sample Complexity, NP-hard
problems, Decidability theory.
V. Koltchinskii is with the Department of Mathematics and Statistics, University of New Mexico, Albuquerque, NM 87131,
USA. E-mail: vlad@math.unm.edu. His research is partially supported by NSA Grant MDA904-99-1-0031
Corresponding Author: C. T. Abdallah is with the Department of EECE, University of New Mexico, Albuquerque, NM

  

Source: Abdallah, Chaouki T- Electrical and Computer Engineering Department, University of New Mexico

 

Collections: Engineering