Title | ||
---|---|---|
Improved sample complexity estimates for statistical learning control of uncertain systems |
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 guar- antee 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 al- gorithms which probabilistically guarantee stability and robustness levels when designing controllers for uncertain systems. |
Year | DOI | Venue |
---|---|---|
2000 | 10.1109/9.895579 | IEEE Trans. Automat. Contr. |
Keywords | Field | DocType |
Statistical learning,Control systems,Uncertain systems,Robust control,Robust stability,Monte Carlo methods,Learning systems,Algorithm design and analysis,Computational complexity,Vectors | Control theory,Robustness (computer science),Artificial intelligence,Robust control,Bootstrapping (electronics),Statistical learning theory,Mathematical optimization,Algorithm design,Approximation theory,Probabilistic method,Machine learning,Mathematics,Computational complexity theory | Journal |
Volume | Issue | ISSN |
45 | 12 | 0018-9286 |
Citations | PageRank | References |
31 | 3.67 | 5 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
V. Koltchinskii | 1 | 118 | 10.42 |
C. T. Abdallah | 2 | 246 | 28.44 |
M. Ariola | 3 | 228 | 25.36 |
P. Dorato | 4 | 224 | 47.00 |
D. Panchenko | 5 | 38 | 4.70 |