Logo eprints

Approximation Error Bounds via Rademacher's Complexity

Gnecco, Giorgio and Sanguineti, Marcello Approximation Error Bounds via Rademacher's Complexity. Applied Mathematical Sciences, 2 (4). pp. 153-176. ISSN 1312-885X (2008)

This is the latest version of this item.

PDF - Published Version
Download (249kB) | Preview


Approximation properties of some connectionistic models, commonly used to construct approximation schemes for optimization problems with multivariable functions as admissible solutions, are investigated. Such models are made up of linear combinations of computational units with adjustable parameters. The relationship between model complexity (number of computational units) and approximation error is investigated using tools from Statistical Learning Theory, such as Talagrand's inequality, fat-shattering dimension, and Rademacher's complexity. For some families of multivariable functions, estimates of the approximation accuracy of models with certain computational units are derived in dependence of the Rademacher's complexities of the families. The estimates improve previously-available ones, which were expressed in terms of V C dimension and derived by exploiting union-bound techniques. The results are applied to approximation schemes with certain radial-basis-functions as computational units, for which it is shown that the estimates do not exhibit the curse of dimensionality with respect to the number of variables.

Item Type: Article
Uncontrolled Keywords: approximation error, model complexity, curse of dimensionality, Rademacher's complexity, Talagrand's inequality, union bounds, VC dimension.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Research Area: Computer Science and Applications
Depositing User: Giorgio Gnecco
Date Deposited: 17 Sep 2013 07:39
Last Modified: 17 Sep 2013 07:39
URI: http://eprints.imtlucca.it/id/eprint/1749

Available Versions of this Item

Actions (login required)

Edit Item Edit Item