LoboVault Home
 

Statistical Learning Control of Uncertain Systems: It is Better Than It Seems

LoboVault

Please use this identifier to cite or link to this item: http://hdl.handle.net/1928/53

Statistical Learning Control of Uncertain Systems: It is Better Than It Seems

Show full item record

Title: Statistical Learning Control of Uncertain Systems: It is Better Than It Seems
Author: Koltchinski, V.; Abdallah, C.T.; Ariola, M.; Dorato, P.; Panchenko, D.
Subject(s): Statistical Learning
Radamacher bootstrap
Robust Control
Sample Complexity
NP-hard problems
Decidability theory
Abstract: Recently, probabilistic methods and statistical learning theory have been shown to provide approximate solutions to \diÆcult" 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 eÆcient algorithms which probabilistically guarantee stability and robustness levels when designing controllers for uncertain systems.
Date: 2000-04-25
Series: EECE-Technical Report-00-001
Description: Technical Report
URI: http://hdl.handle.net/1928/53

Files in this item

Files Size Format View
eece-tr-00-001.pdf 493.8Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record

UNM Libraries

Search LoboVault


Advanced Search

Browse

My Account