Sequential prediction of individual sequences under general loss functions

DOI10.1109/18.705569zbMath1026.68579OpenAlexW2147632820MaRDI QIDQ4701166

David Haussler, Manfred K. Warmuth, Jyrki Kivinen

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/10.1109/18.705569

zbMATH Keywords

data compressionbinary sequencesforecastingregreton-line learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Communication theory (94A05)

Related Items (23)

Fast learning rates in statistical inference through aggregation ⋮ Unnamed Item ⋮ Competitive On-line Statistics ⋮ Efficient learning with virtual threshold gates ⋮ The Fundamental Nature of the Log Loss Function ⋮ A Bayesian approach to (online) transfer learning: theory and algorithms ⋮ Sparse regression learning by aggregation and Langevin Monte-Carlo ⋮ Mirror averaging with sparsity priors ⋮ Loss functions, complexities, and the Legendre transformation. ⋮ Universal prediction of random binary sequences in a noisy environment ⋮ Randomized prediction of individual sequences ⋮ Learning by mirror averaging ⋮ The weak aggregating algorithm and weak mixability ⋮ Optimal learning with Bernstein Online Aggregation ⋮ Probability theory for the Brier game ⋮ Supermartingales in prediction with expert advice ⋮ Regression Estimation from an Individual Stable Sequence ⋮ Generalized mirror averaging and \(D\)-convex aggregation ⋮ Robust forecast combinations ⋮ Sensor networks: from dependence analysis via matroid bases to online synthesis ⋮ Prediction with Expert Evaluators’ Advice ⋮ How many strings are easy to predict? ⋮ Does snooping help?

This page was built for publication: Sequential prediction of individual sequences under general loss functions