Universally consistent online learning with arbitrarily dependent responses

MaRDI QIDQ7028769zbMATH OpenFDO

Authors Steve Hanneke

Publication date 11 February 2025

Full work available at URL https://proceedings.mlr.press/v167/hanneke22a.html

zbMATH Keywords

non-ergodic processesnonparametric estimationonline learningstationary processesstatistical learning theorystochastic processesuniversal consistency

Mathematics Subject Classification ID

Prediction theory (aspects of stochastic processes) (60G25) Nonparametric regression and quantile regression (62G08) Inference from stochastic processes and prediction (62M20) Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Cites work

• A decision-theoretic generalization of on-line learning and an application to boosting
• A distribution-free theory of nonparametric regression
• A simple randomized algorithm for sequential prediction of ergodic time series
• Consistent nonparametric regression. Discussion
• Data-dependent k/sub n/-NN and kernel estimators consistent for arbitrary processes
• How to use expert advice
• scientific article; zbMATH DE number 3128728 (Why is no real title available?)
• scientific article; zbMATH DE number 893887 (Why is no real title available?)
• Learning from dependent observations
• Learning whenever learning is possible: universal learning under general stochastic processes
• Nonparametric inference for ergodic, stationary time series
• Nonparametric sequential prediction of stationary time series
• Online learning via sequential complexities
• Pattern recognition for conditionally independent data
• Prediction, Learning, and Games
• Regression Estimation from an Individual Stable Sequence
• The weighted majority algorithm
• Universal Bayes consistency in metric spaces
• Universal forecasting algorithms
• Universal linear prediction by model order weighting

This page was built for publication: Universally consistent online learning with arbitrarily dependent responses

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7028769)