PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Learning, Regularization and Ill-Posed Inverse Problems
Lorenzo Rosasco, Andrea Caponnetto, Ernesto De Vito, Umberto De Giovannini and Francesca Odone
In: nips 2004, 13-18 2004, vancouver canada.


Many works have shown that strong connections relate learning from examples to regularization techniques for ill-posed inverse problems. Nevertheless by now there was no formal evidence neither that learning from examples could be seen as an inverse problem nor that theoretical results in learning theory could be independently derived using tools from regularization theory. In this paper we provide a positive answer to both questions. Indeed, considering the square loss, we translate the learning problem in the language of regularization theory and show that consistency results and optimal regularization parameter choice can be derived by the discretization of the corresponding inverse problem.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Theory & Algorithms
ID Code:415
Deposited By:Lorenzo Rosasco
Deposited On:03 January 2005