A Bernstein-type inequality for some mixing processes and dynamical systems with an application to learning

DOI10.1214/16-AOS1465zbMath1388.60060arXiv1501.03059OpenAlexW2963245453MaRDI QIDQ2012203

Ingo Steinwart, Hanyuan Hang

Publication date: 28 July 2017

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1501.03059

zbMATH Keywords

dynamical systemssupport vector machines (SVMs)Bernstein-type inequalitiesmixing processesnonparametric classification and regression

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Inequalities; stochastic orderings (60E15) Stationary stochastic processes (60G10) Learning and adaptive systems in artificial intelligence (68T05) Large deviations (60F10) Uniformly hyperbolic systems (expanding, Anosov, Axiom A, etc.) (37D20)

Related Items

On the need for structure modelling in sequence prediction ⋮ Exponential inequalities for nonstationary Markov chains ⋮ Local linear regression with nonparametrically generated covariates for weakly dependent data ⋮ Structure learning via unstructured kernel-based M-estimation ⋮ Recovery guarantees for polynomial coefficients from weakly dependent data with outliers ⋮ Empirical risk minimization and complexity of dynamical models ⋮ Learning Theory Estimates with Observations from General Stationary Stochastic Processes ⋮ Unnamed Item ⋮ Unnamed Item ⋮ An extension of Bernstein inequality ⋮ Concentration of weakly dependent Banach-valued sums and applications to statistical learning methods ⋮ Robbins-Monro algorithm with \(\psi\)-mixing random errors ⋮ Gibbs posterior convergence and the thermodynamic formalism