LQG online learning
From MaRDI portal
Abstract: Optimal control theory and machine learning techniques are combined to formulate and solve in closed form an optimal control formulation of online learning from supervised examples with regularization of the updates. The connections with the classical Linear Quadratic Gaussian (LQG) optimal control problem, of which the proposed learning paradigm is a non-trivial variation as it involves random matrices, are investigated. The obtained optimal solutions are compared with the Kalman-filter estimate of the parameter vector to be learned. It is shown that the proposed algorithm is less sensitive to outliers with respect to the Kalman estimate (thanks to the presence of the regularization term), thus providing smoother estimates with respect to time. The basic formulation of the proposed online-learning framework refers to a discrete-time setting with a finite learning horizon and a linear model. Various extensions are investigated, including the infinite learning horizon and, via the so-called "kernel trick", the case of nonlinear models.
Recommendations
- Linear quadratic optimal learning control (LQL)
- Logarithmic regret in online linear quadratic control using Riccati updates
- Model-free linear quadratic regulator
- Q-learning for continuous-time linear systems: A model-free infinite horizon optimal control approach
- Optimal Control of an Unknown Linear Process with Learning
Cites work
- \(H^ \infty\)-optimal control and related minimax design problems. A dynamic game approach.
- A linear systems primer.
- A simpler approach to matrix completion
- An introduction to support vector machines and other kernel-based learning methods.
- Approximate dynamic programming for stochastic \(N\)-stage optimization with application to optimal consumption under uncertainty
- Best choices for regularization parameters in learning theory: on the bias-variance problem.
- Discrete-time stochastic systems. Estimation and control.
- Dynamic programming and value-function approximation in sequential decision problems: error analysis and numerical results
- Extended Kernel Recursive Least Squares Algorithm
- Foundations of support constraint machines
- Graph theoretic methods in multiagent networks
- Hilbert space, boundary value problems and orthogonal polynomials
- scientific article; zbMATH DE number 3890132 (Why is no real title available?)
- scientific article; zbMATH DE number 4068688 (Why is no real title available?)
- scientific article; zbMATH DE number 3718879 (Why is no real title available?)
- scientific article; zbMATH DE number 1321699 (Why is no real title available?)
- scientific article; zbMATH DE number 1022658 (Why is no real title available?)
- scientific article; zbMATH DE number 1095138 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 3304505 (Why is no real title available?)
- Incremental Least Squares Methods and the Extended Kalman Filter
- Inequalities for the trace of matrix product
- Introduction to Stochastic Search and Optimization
- Introduction to the Mathematical and Satistical Foundations of Econometrics
- Kalman filtering. Theory and practice with MATLAB
- Learning with boundary conditions
- Manifold regularization: a geometric framework for learning from labeled and unlabeled examples
- Matrix mathematics. Theory, facts, and formulas
- Model predictive control. With a foreword by M. J. Grimble and M. A. Johnson
- Moving-horizon estimation with guaranteed robustness for discrete-time linear systems and measurements subject to outliers
- Online gradient descent learning algorithms
- Online learning algorithms
- Online learning and online convex optimization
- Online learning with (multiple) kernels: a review
- Output outlier robust state estimation
- Reinforcement learning. An introduction
- STATISTICAL LEARNING WITH TIME-VARYING PARAMETERS
- Stochastic models, estimation, and control. Vol. 2,3
- Suboptimal solutions to dynamic optimization problems via approximations of the policy functions
Cited in
(5)- On the trade-off between number of examples and precision of supervision in machine learning problems
- Control-based algorithms for high dimensional online learning
- scientific article; zbMATH DE number 5957431 (Why is no real title available?)
- Regret bounds for online-learning-based linear quadratic control under database attacks
- Data-driven performance metrics for neural network learning
This page was built for publication: LQG online learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380837)
