Aggregating Algorithm for Prediction of Packs
This work addresses a specific case of delayed feedback prediction for machine learning applications, but it is incremental as it adapts existing methods to a new protocol.
The paper tackles the problem of prediction under delayed feedback, specifically for packs where multiple predictions are made before outcomes are revealed, by developing theory and algorithms based on Vovk's Aggregating Algorithm, resulting in tight upper bounds and empirical validation on housing data.
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.