Journal ArticleDOI
A learning theory approach to system identification and stochastic adaptive control
Reads0
Chats0
TLDR
This chapter presents an approach to system identification based on viewing identification as a problem in statistical learning theory, and a result is derived showing that in the case of systems with fading memory, it is possible to combine standard results in statisticallearning theory with some fading memory arguments to obtain finite time estimates of the desired kind.About:
This article is published in Journal of Process Control.The article was published on 2008-03-01. It has received 70 citations till now. The article focuses on the topics: Algorithmic learning theory & Statistical learning theory.read more
Citations
More filters
Journal ArticleDOI
On the Sample Complexity of the Linear Quadratic Regulator
TL;DR: This paper proposes a multi-stage procedure that estimates a model from a few experimental trials, estimates the error in that model with respect to the truth, and then designs a controller using both the model and uncertainty estimate, and provides end-to-end bounds on the relative error in control cost.
Posted Content
A Tour of Reinforcement Learning: The View from Continuous Control
TL;DR: This article surveys reinforcement learning from the perspective of optimization and control, with a focus on continuous control applications.
Proceedings Article
Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification
TL;DR: In this paper, the authors show that the OLS estimator attains nearly minimax optimal performance for the identification of linear dynamical systems from a single observed trajectory, using a generalization of Mendelson's small-ball method to dependent data, eschewing the use of standard mixing-time arguments.
Posted Content
Gradient Descent Learns Linear Dynamical Systems
TL;DR: In this paper, the authors proved that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamical system from a sequence of noisy observations generated by the system.
Proceedings ArticleDOI
Finite Sample Analysis of Stochastic System Identification
TL;DR: In this article, the authors analyze the finite sample complexity of stochastic system identification using modern tools from machine learning and statistics, and provide non-asymptotic high-probability upper bounds for the system parameter estimation errors.
References
More filters
Book
Markov Chains and Stochastic Stability
Sean P. Meyn,Richard L. Tweedie +1 more
TL;DR: This second edition reflects the same discipline and style that marked out the original and helped it to become a classic: proofs are rigorous and concise, the range of applications is broad and knowledgeable, and key ideas are accessible to practitioners with limited mathematical background.
Book ChapterDOI
On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
TL;DR: This chapter reproduces the English translation by B. Seckler of the paper by Vapnik and Chervonenkis in which they gave proofs for the innovative results they had obtained in a draft form in July 1966 and announced in 1968 in their note in Soviet Mathematics Doklady.
Journal ArticleDOI
Optimal robustness in the gap metric
TL;DR: In this article, a solution to the problem of robustness optimization in the gap metric is presented, and the least amount of combined controller uncertainty that can cause instability of a nominally stable feedback system is determined.
Journal ArticleDOI
Convergence analysis of parametric identification methods
TL;DR: A certain class of methods to select suitable models of dynamical stochastic systems from measured input-output data is considered, based on a comparison between the measured outputs and the outputs of a candidate model.
Book
A Theory of Learning and Generalization
TL;DR: This new edition, with substantial new material, takes account of important new developments in the theory of learning and deals extensively with the Theory of learning control systems, which has now reached a level of maturity comparable to that of learning of neural networks.