Universal schemes for learning the best nonlinear predictor given the infinite past and side information

DOI10.1109/18.761258zbMath0959.62078OpenAlexW2164376107MaRDI QIDQ4701368

Paul H. Algoet

Publication date: 21 November 1999

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

Full work available at URL: https://doi.org/10.1109/18.761258

zbMATH Keywords

predictiontime seriesforecastinginferencerecurrence timeslearning from experience

Mathematics Subject Classification ID

Inference from stochastic processes and prediction (62M20) Nonparametric regression and quantile regression (62G08) Communication, information (94A99)

Related Items (17)

Asymptotic confidence intervals for Poisson regression ⋮ Intermittent estimation of stationary time series ⋮ ON SEQUENTIAL ESTIMATION AND PREDICTION FOR DISCRETE TIME SERIES ⋮ Unnamed Item ⋮ Estimating the conditional expectations for continuous time stationary processes ⋮ A universal strong law of large numbers for conditional expectations via nearest neighbors ⋮ Application of data compression methods to nonparametric estimation of characteristics of discrete-time stochastic processes ⋮ On universal estimates for binary renewal processes ⋮ Nonparametric sequential prediction for stationary processes ⋮ Universal codes as a basis for nonparametric testing of serial independence for time series ⋮ On universal algorithms for classifying and predicting stationary processes ⋮ Strong universal pointwise consistency of some regression function estimates ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Experimental investigation of forecasting methods based on data compression algorithms ⋮ On asymptotically optimal methods of prediction and adaptive coding for Markov sources ⋮ Unnamed Item

This page was built for publication: Universal schemes for learning the best nonlinear predictor given the infinite past and side information