One of the main problems in machine learning and statistical inference is selecting an appropriate model by which a set of data can be explained. A novel model selection criterion based on the uniform convergence of empirical processes combined with the results concerning the approximation ability of non-linear manifolds of functions is introduced. A coherent and robust framework for model selection was elucidated and a lower bound on the approximation error was established, giving a well specified sense for most functions of interest.
|Number of pages||11|
|State||Published - 1 Jan 1996|
|Event||Proceedings of the 1996 9th Annual Conference on Computational Learning Theory - Desenzano del Garda, Italy|
Duration: 28 Jun 1996 → 1 Jul 1996
|Conference||Proceedings of the 1996 9th Annual Conference on Computational Learning Theory|
|City||Desenzano del Garda, Italy|
|Period||28/06/96 → 1/07/96|