Nonparametric sequential prediction for stationary processes

DOI10.1214/10-AOP576zbMATH Open1301.60052arXiv1104.1555MaRDI QIDQ533751FDOQ533751

Gusztáv Morvai, Benjamin Weiss

Publication date: 6 May 2011

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

Abstract: We study the problem of finding an universal estimation scheme $h_n:mathbb{R}^{n}omathbbR$, $n=1,2,\mathrm{...}$ which will satisfy lim_{t ightarrowinfty}{frac{1}{t}}sum_{i=1}^t|h_ i(X_0,X_1,...,X_{i-1})-E(X_i|X_0,X_1,...,X_{i-1})|^p=0 a.s. for all real valued stationary and ergodic processes that are in $L^p$. We will construct a single such scheme for all $1<pleinfty$, and show that for $p=1$ mere integrability does not suffice but $Llo{g}^{+}L$ does.

Full work available at URL: https://arxiv.org/abs/1104.1555

zbMATH Keywords

stationary processesnonparametric predicton

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Prediction theory (aspects of stochastic processes) (60G25) Stationary stochastic processes (60G10)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• A distribution-free theory of nonparametric regression
• Inequalities for the $r$th Absolute Moment of a Sum of Random Variables, $1 \leqq r \leqq 2$
• Ergodic theorems. With a supplement by Antoine Brunel
• Splitting a Single State of a Stationary Process into Markovian States
• A law of large numbers for identically distributed martingale differences
• Limits to consistent on-line forecasting for ergodic time series
• Prediction of random sequences and universal coding
• Nonparametric inference for ergodic, stationary time series
• Prediction for discrete time series
• Universal schemes for prediction, gambling and portfolio selection
• Guessing the next output of a stationary process
• Forward estimation for ergodic time series
• Sequential Prediction of Unbounded Stationary Time Series
• Weakly convergent nonparametric forecasting of stationary time series
• A simple randomized algorithm for sequential prediction of ergodic time series
• On estimating the memory for finitarily Markovian processes
• Finitarily deterministic generators for zero entropy systems
• Forecasting for stationary binary time series
• Intermittent estimation of stationary time series
• Limitations on intermittent forecasting
• On classifying processes
• The ergodic theorem for a sequence of functions
• On optimal sequential prediction for general processes
• Universal prediction
• Universal schemes for learning the best nonlinear predictor given the infinite past and side information
• The strong law of large numbers for sequential decisions under uncertainty
• Inferring the conditional mean

Cited In (7)

• Weakly universally consistent static forecasting of stationary and ergodic time series via local averaging and least squares estimates
• Estimating the conditional expectations for continuous time stationary processes
• Predicting non-stationary processes
• Gaussian process for nonstationary time series prediction
• On the non-parametric prediction of conditionally stationary sequences
• On universal algorithms for classifying and predicting stationary processes
• Title not available (Why is that?)

This page was built for publication: Nonparametric sequential prediction for stationary processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q533751)