Sequential Prediction of Unbounded Stationary Time Series

DOI10.1109/TIT.2007.894660zbMath1314.62215OpenAlexW2129962685MaRDI QIDQ3548154

László Györfi, György Ottucsák

Publication date: 21 December 2008

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/tit.2007.894660

zbMATH Keywords

pattern recognitiontime serieson-line learninguniversal consistencysequential prediction

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Related Items

Unnamed Item ⋮ Long‐term prediction intervals with many covariates ⋮ Weakly universally consistent static forecasting of stationary and ergodic time series via local averaging and least squares estimates ⋮ Unnamed Item ⋮ Universal regression with adversarial responses ⋮ Estimating the conditional expectations for continuous time stationary processes ⋮ Universal rates for estimating the residual waiting time in an intermittent way ⋮ Nonparametric sequential prediction of time series ⋮ Nonparametric sequential prediction for stationary processes ⋮ An Open Problem on Strongly Consistent Learning of the Best Prediction for Gaussian Processes ⋮ On universal algorithms for classifying and predicting stationary processes ⋮ Unnamed Item