Aggregating algorithm for prediction of packs

DOI10.1007/S10994-018-5769-2zbMATH Open1493.68288arXiv1710.08114OpenAlexW2963429749WikidataQ128682526 ScholiaQ128682526MaRDI QIDQ2320552FDOQ2320552

Authors: Dmitry Adamskiy, Anthony Bellotti, Raisa Dzhamtyrova, Yuri Kalnishkan 

Publication date: 23 August 2019

Published in: Machine Learning (Search for Journal in Brave)

Abstract: This paper formulates the protocol for prediction of packs, which a special case of prediction under delayed feedback. Under this protocol, the learner must make a few predictions without seeing the outcomes and then the outcomes are revealed. We develop the theory of prediction with expert advice for packs. By applying Vovk's Aggregating Algorithm to this problem we obtain a number of algorithms with tight upper bounds. We carry out empirical experiments on housing data.

Full work available at URL: https://arxiv.org/abs/1710.08114

Recommendations

• Prediction with expert evaluators' advice
• Prediction with Expert Advice under Discounted Loss
• Learning Theory
• On delayed prediction of individual sequences
• The weak aggregating algorithm and weak mixability

zbMATH Keywords

machine learningsportonline learninghouse pricesprediction with expert advice

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27)

Cites Work

• Prediction, Learning, and Games
• Title not available (Why is that?)
• The weighted majority algorithm
• A game of prediction with expert advice
• Competitive On-line Statistics
• Loss functions, complexities, and the Legendre transformation.
• Prediction with expert advice for the Brier game
• Reliable region predictions for automated valuation models
• A closer look at adaptive regret
• On delayed prediction of individual sequences

This page was built for publication: Aggregating algorithm for prediction of packs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2320552)