Bayesian frequentist bounds for machine learning and system identification

DOI10.1016/j.automatica.2022.110599zbMath1504.93388OpenAlexW4296167629MaRDI QIDQ2097759

Giacomo Baggio, Algo Carè, Anna Scampicchio, Gianluigi Pillonetto

Publication date: 14 November 2022

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2022.110599

zbMATH Keywords

system identificationuncertainty quantificationGaussian regressionfinite sample system identificationkernel-based non-parametric methods

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Identification in stochastic control theory (93E12)

Uses Software

• BayesDA
• ElemStatLearn
• Gibbsit

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Kernel methods in system identification, machine learning and function estimation: a survey
• Optimal learning rates for least squares regularized regression with unbounded sampling
• A reproducing kernel Hilbert space approach to functional linear regression
• Optimal rates for regularization of statistical inverse learning problems
• A new kernel-based approach for linear system identification
• The interplay of Bayesian and frequentist analysis
• Concentration estimates for learning with unbounded sampling
• Regularization networks and support vector machines
• Non-asymptotic confidence regions for regularized linear regression estimates
• On the sample complexity of the linear quadratic regulator
• Facing undermodelling in sign-perturbed-sums system identification
• Distribution-free uncertainty quantification for kernel methods by gradient perturbations
• Asymptotic properties of SPS confidence regions
• Learning rates of least-square regularized regression
• Guaranteed non-asymptotic confidence regions in system identification
• Learning theory estimates via integral operators and their approximations
• The Bayesian Lasso
• Generalized Cross-Validation as a Method for Choosing a Good Ridge Parameter
• Nonparametric estimation of transfer functions: rates of convergence and adaptation
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Sign-Perturbed Sums: A New System Identification Approach for Constructing Exact Non-Asymptotic Confidence Regions in Linear Regression Models
• Particle Markov Chain Monte Carlo Methods
• Bayes Factors
• The Bayesian Bridge
• An $\ell _{1}$-Laplace Robust Kalman Smoother
• A Correspondence Between Bayesian Estimation on Stochastic Processes and Smoothing by Splines
• Theory of Reproducing Kernels
• Robust Statistics
• Matrix theory. Basic results and techniques
• The elements of statistical learning. Data mining, inference, and prediction