arXiv:1710.08114 [cs.LG]AbstractReferencesReviewsResources
Aggregating Algorithm for Prediction of Packs
Dmitry Adamskiy, Tony Bellotti, Raisa Dzhamtyrova, Yuri Kalnishkan
Published 2017-10-23Version 1
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.
Categories: cs.LG
Related articles: Most relevant | Search more
arXiv:1003.2218 [cs.LG] (Published 2010-03-10)
Supermartingales in Prediction with Expert Advice
arXiv:1705.01091 [cs.LG] (Published 2017-05-02)
PDE approach to the problem of online prediction with expert advice: a construction of potential-based strategies
arXiv:2011.01217 [cs.LG] (Published 2020-10-31)
Prediction against limited adversary