Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization

Author: Mukherjee Sayan   Niyogi Partha   Poggio Tomaso   Rifkin Ryan  

Publisher: Springer Publishing Company

ISSN: 1019-7168

Source: Advances in Computational Mathematics, Vol.25, Iss.1-3, 2006-07, pp. : 161-193

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract