Well-calibrated predictions from on-line compression models

DOI10.1016/j.tcs.2006.07.038zbMath1153.68434OpenAlexW2155868408WikidataQ62046736 ScholiaQ62046736MaRDI QIDQ860821

Vladimir Vovk

Publication date: 9 January 2007

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.tcs.2006.07.038

zbMATH Keywords

Gaussian modelMarkov modelGauss linear modelconfidence transducerexchangeability modelhypergraphical modelon-line compression modellingtransductive confidence machine

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Extremal families and systems of sufficient statistics
• Algebraic algorithms for sampling from conditional distributions
• Kolmogorov's contributions to the foundations of probability
• On the concept of the Bernoulli property
• Combinatorial foundations of information theory and the calculus of probabilities
• Some Properties of Kolmogorov $\Delta$-Random Finite Sequences
• Logical basis for information theory and probability theory
• Invariants Under Mixing which Generalize de Finetti's Theorem
• The definition of random sequences
• The Probability That the Mean of a Second Sample Will Differ from the Mean of a First Sample By Less Than a Certain Multiple of the Standard Deviation of the First Sample
• Determination of Sample Sizes for Setting Tolerance Limits
• Algorithmic Learning Theory

This page was built for publication: Well-calibrated predictions from on-line compression models