Improved risk tail bounds for on-line algorithms
Nicolò Cesa-Bianchi and Claudio Gentile
IEEE Transactions on Information Theory Volume 54, Number 1, pp. 386-390, 2008.

This is the latest version of this eprint.

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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.

Available Versions of this Item

• Improved risk tail bounds for on-line algorithms (deposited 28 November 2005)
  • Improved risk tail bounds for on-line algorithms (deposited 14 February 2008) [Currently Displayed]

[Edit]