Statistical learning control of uncertain systems: theory and algorithms.
It is well known that control problems can be solved very seldomly exactly. On the other hand, many of the control problems can be reduced to decidability or optimization problems and, moreover, probabilistic methods (based on the Monte Carlo approach) can be employed to solve the new problems approximately. To obtain an accuracy of these methods, the Chernoff Bounds, the Hoeffding Inequality (or generally empirical processes and statistical learning theory) can be employed. However, it is known (from the literature) that a large number of the random samples can only (in this approach) guarantee the accuracy. The authors of the paper suggest another approach. They suggest bootstrap sequential learning algorithms based on Rademacher bootstrap (or other bootstrap techniques). A random number of samples (known as the sample complexity of learning) appears in such algorithms. The theoretical, ``underlying assertions are recalled here; however, their proofs can be found in a former paper of V. Koltchinskii, C. T. Adallah and M. Ariola. The introduced algorithm is illustrated on an example, already known from the literature. The paper is written in an understandable way.
- Improved sample complexity estimates for statistical learning control of uncertain systems
- Stochastic algorithms for robustness of control performances
- scientific article; zbMATH DE number 1679747
- Statistical learning methods in linear algebra and control problems: The example of finite-time control of uncertain linear systems
- Randomized algorithms for robust controller synthesis using statistical learning theory
- A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations
- A Monte Carlo approach to the analysis of control system robustness
- scientific article; zbMATH DE number 3168214 (Why is no real title available?)
- scientific article; zbMATH DE number 1332320 (Why is no real title available?)
- scientific article; zbMATH DE number 749988 (Why is no real title available?)
- scientific article; zbMATH DE number 893887 (Why is no real title available?)
- scientific article; zbMATH DE number 926775 (Why is no real title available?)
- Improved sample complexity estimates for statistical learning control of uncertain systems
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- Statistical learning methods in linear algebra and control problems: The example of finite-time control of uncertain linear systems
- Statistical learning for probability-constrained stochastic optimal control
- Research on probabilistic methods for control system design
- Improvement of algorithm on the track recognition
- Control analysis and synthesis of data-driven learning for uncertain linear systems
- Improved sample complexity estimates for statistical learning control of uncertain systems
- A statistical analysis of certain iterative learning control algorithms
- Machine Learning and Control Theory
This page was built for publication: Statistical learning control of uncertain systems: theory and algorithms.
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1854969)
