Exponential inequalities for nonstationary Markov chains
From MaRDI portal
Publication:2178936
exponential inequalitiesmartingalesmodel selectionnonstationary Markov chainsoracle inequalitiesstatistical learning theorytime series forecasting
Inequalities; stochastic orderings (60E15) Discrete-time Markov processes on general state spaces (60J05) Markov processes: estimation; hidden Markov models (62M05) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Inference from stochastic processes and prediction (62M20) Computational learning theory (68Q32)
Abstract: Exponential inequalities are main tools in machine learning theory. To prove exponential inequalities for non i.i.d random variables allows to extend many learning techniques to these variables. Indeed, much work has been done both on inequalities and learning theory for time series, in the past 15 years. However, for the non independent case, almost all the results concern stationary time series. This excludes many important applications: for example any series with a periodic behavior is non-stationary. In this paper, we extend the basic tools of Dedecker and Fan (2015) to nonstationary Markov chains. As an application, we provide a Bernstein-type inequality, and we deduce risk bounds for the prediction of periodic autoregressive processes with an unknown period.
Recommendations
- Exponential concentration inequalities for additive functionals of Markov chains
- New Bernstein and Hoeffding type inequalities for regenerative Markov chains
- New Bernstein's inequalities for dependent observations and applications to learning theory
- Hoeffding's inequality for uniformly ergodic Markov chains
- Generalization bounds for non-stationary mixing processes
Cites work
- A Bernstein type inequality and moderate deviations for weakly dependent sequences
- A Bernstein-type inequality for some mixing processes and dynamical systems with an application to learning
- A general class of exponential inequalities for martingales and ratios
- A tail inequality for suprema of unbounded empirical processes with applications to Markov chains
- Asymptotic Theory of Weakly Dependent Random Processes
- Bernstein inequality and moderate deviations under strong mixing conditions
- Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
- Concentration inequalities for dependent random variables via the martingale method
- Concentration inequalities for Markov chains by Marton couplings and spectral methods
- Concentration inequalities for sums and martingales
- Concentration inequalities. A nonasymptotic theory of independence
- Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
- Concentration of weakly dependent Banach-valued sums and applications to statistical learning methods
- Curvature, concentration and error estimates for Markov chain Monte Carlo
- Deviation inequalities for separately Lipschitz functionals of iterated random functions
- Deviation inequalities for sums of weakly dependent time series
- Exponential inequalities for dynamical measures of expanding maps of the interval
- Exponential inequalities for martingales, with application to maximum likelihood estimation for counting processes
- Exponential inequalities for unbounded functions of geometrically ergodic Markov chains: applications to quantitative error bounds for regenerative Metropolis algorithms
- Extensions of the Hoeffding-Azuma inequalities
- Fast learning from \(\alpha\)-mixing observations
- scientific article; zbMATH DE number 1332320 (Why is no real title available?)
- Iterated Random Functions
- Laplace transform estimates and deviation inequalities
- Learning from dependent observations
- Minimal penalties for Gaussian model selection
- Minimum complexity regression estimation with weakly dependent observations
- Model selection for weakly dependent time series forecasting
- New Bernstein and Hoeffding type inequalities for regenerative Markov chains
- Non-parametric estimation of time varying AR(1)-processes with local stationarity and periodicity
- Nonparametric risk bounds for time-series forecasting
- Nonparametric time series prediction through adaptive model selection
- On McDiarmid's concentration inequality
- On the Kullback-Leibler information divergence of locally stationary processes
- Optimal model selection for density estimation of stationary data under various mixing condi\-tions
- PAC-Bayesian Inequalities for Martingales
- Prediction of time series by statistical learning: general losses and fast rates
- Probability and moment inequalities for sums of weakly dependent random variables, with applications
- Rademacher complexity for Markov chains: applications to kernel smoothing and Metropolis-Hastings
- Sharp bounds for the tails of functionals of Markov chains
- Simpler PAC-Bayesian bounds for hostile data
- Slope heuristics: overview and implementation
- Stochastic models for time series
- Weak dependence. With examples and applications.
Cited in
(8)- A deviation inequality for non-reversible Markov processes
- Robbins-Monro algorithm with \(\psi\)-mixing random errors
- Concentration inequalities for non-causal random fields
- Concurrent neural network: a model of competition between times series
- Deviation inequalities for stochastic approximation by averaging
- High-dimensional VAR with low-rank transition
- Rademacher learning rates for iterated random functions
- Testing stationarity and change point detection in reinforcement learning
This page was built for publication: Exponential inequalities for nonstationary Markov chains
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2178936)
