Tight bounds are derived on the risk of models in the ensemble generated by incremental training of an arbitrary learning algorithm. The result is based on proof techniques that are remarkably different from the standard risk analysis based on uniform convergence arguments, and improves on previous bounds published by the same authors.
Improved risk tail bounds for on-Line algorithms / N. Cesa-Bianchi, C. Gentile. - In: IEEE TRANSACTIONS ON INFORMATION THEORY. - ISSN 0018-9448. - 54:1(2008), pp. 386-390.
Improved risk tail bounds for on-Line algorithms
N. Cesa-BianchiPrimo
;
2008
Abstract
Tight bounds are derived on the risk of models in the ensemble generated by incremental training of an arbitrary learning algorithm. The result is based on proof techniques that are remarkably different from the standard risk analysis based on uniform convergence arguments, and improves on previous bounds published by the same authors.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
