Competing with Stationary Prediction Strategies

DOI10.1007/978-3-540-72927-3_32MaRDI QIDQ5434067zbMATH OpenOpenAlexFDO

Authors Vladimir Vovk

Publication date 3 January 2008

Published in Learning Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cs/0607067

Mathematics Subject Classification ID

Stationary stochastic processes (60G10) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: In this paper we introduce the class of stationary prediction strategies and construct a prediction algorithm that asymptotically performs as well as the best continuous stationary strategy. We make mild compactness assumptions but no stochastic assumptions about the environment. In particular, no assumption of stationarity is made about the environment, and the stationarity of the considered strategies only means that they do not depend explicitly on time; we argue that it is natural to consider only stationary strategies even for highly non-stationary environments.

Recommendations

• Nonparametric sequential prediction of stationary time series
• Sequential Prediction of Unbounded Stationary Time Series
• Leading Strategies in Competitive On-Line Prediction
• Leading strategies in competitive on-line prediction
• Online prediction

Cited in

(6)

• Behavior strategy in a stationary environment with an unimprovable guaranteed mean-income convergence bound
• Revisiting Francis Galton's forecasting competition
• Strategies for Prediction Under Imperfect Monitoring
• scientific article; zbMATH DE number 908756 (Why is no real title available?)
• Competitive Statistical Estimation With Strategic Data Sources
• Prediction of locally stationary data using expert advice

This page was built for publication: Competing with Stationary Prediction Strategies

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5434067)