On-line maximum likelihood prediction with respect to general loss functions

DOI10.1006/JCSS.1997.1503zbMATH Open0880.68053OpenAlexW2009207556MaRDI QIDQ1370862FDOQ1370862

Authors: Kenji Yamanishi 

Publication date: 28 October 1997

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jcss.1997.1503

Recommendations

• A loss bound model for on-line stochastic prediction algorithms
• Relative loss bounds for on-line density estimation with the exponential family of distributions
• Worst-case bounds for the logarithmic loss of predictors
• Relative expected instantaneous loss bounds

zbMATH Keywords

on-line prediction algorithmsparametric probabilistic models

Mathematics Subject Classification ID

Parallel algorithms in computer science (68W10)

Cites Work

• Title not available (Why is that?)
• Present Position and Potential Developments: Some Personal Views: Statistical Theory: The Prequential Approach
• Title not available (Why is that?)
• Minimum complexity density estimation
• A universal prior for integers and estimation by minimum description length
• The weighted majority algorithm
• Information-theoretic asymptotics of Bayes methods
• Universal coding, information, prediction, and estimation
• Title not available (Why is that?)
• Title not available (Why is that?)
• A learning criterion for stochastic rules
• A universal data compression system
• Title not available (Why is that?)
• Efficient distribution-free learning of probabilistic concepts
• On the Assumptions Used to Prove Asymptotic Normality of Maximum Likelihood Estimates
• The strong law of large numbers for sequential decisions under uncertainty
• A loss bound model for on-line stochastic prediction algorithms
• Best ?- and N ?-approximants in Orlicz spaces of vector valued functions

Cited In (10)

• A loss bound model for on-line stochastic prediction algorithms
• Relative loss bounds for on-line density estimation with the exponential family of distributions
• The fundamental nature of the log loss function
• Algorithmic Learning Theory
• Title not available (Why is that?)
• Global implicit function theorems and the online expectation–maximisation algorithm
• Title not available (Why is that?)
• Leading Strategies in Competitive On-Line Prediction
• Online inference with multi-modal likelihood functions
• Leading strategies in competitive on-line prediction

This page was built for publication: On-line maximum likelihood prediction with respect to general loss functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1370862)