Abstract
We introduce a new protocol for prediction with expert advice in which each expert evaluates the learner’s and his own performance using a loss function that may change over time and may be different from the loss functions used by the other experts. The learner’s goal is to perform better or not much worse than each expert, as evaluated by that expert, for all experts simultaneously. If the loss functions used by the experts are all proper scoring rules and all mixable, we show that the defensive forecasting algorithm enjoys the same performance guarantee as that attainable by the Aggregating Algorithm in the standard setting and known to be optimal. This result is also applied to the case of “specialist” experts. In this case, the defensive forecasting algorithm reduces to a simple modification of the Aggregating Algorithm.Citation
Chernov. A. and Vovk, V., (2009) 'Prediction with Expert Evaluators’ Advice' in Algorithmic Learning Theory, proceedings of the 20th International Conference, ALT 2009, vol. 5809: 8-22Publisher
SpringerJournal
Algorithmic Learning TheoryType
Conference papers, meetings and proceedingsLanguage
enISBN
9783642044137ae974a485f413a2113503eed53cd6c53
10.1007/978-3-642-04414-4_6