Improved Generalization via Tolerant Training

W. N. Street and O. L. Mangasarian
Additional contact information
W. N. Street: Oklahoma State University
O. L. Mangasarian: University of Wisconsin

Journal of Optimization Theory and Applications, 1998, vol. 96, issue 2, No 1, 259-279

Abstract: Abstract Theoretical and computational justification is given for improved generalization when the training set is learned with less accuracy. The model used for this investigation is a simple linear one. It is shown that learning a training set with a tolerance τ improves generalization, over zero-tolerance training, for any testing set satisfying a certain closeness condition to the training set. These results, obtained via a mathematical programming formulation, are placed in the context of some well-known machine learning results. Computational confirmation of improved generalization is given for linear systems (including nine of the twelve real-world data sets tested), as well as for nonlinear systems such as neural networks for which no theoretical results are available at present. In particular, the tolerant training method improves generalization on noisy, sparse, and overparameterized problems.

Keywords: Inductive learning; function approximation; generalization (search for similar items in EconPapers)
Date: 1998
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://link.springer.com/10.1023/A:1022664513146 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joptap:v:96:y:1998:i:2:d:10.1023_a:1022664513146

Ordering information: This journal article can be ordered from
http://www.springer. ... cs/journal/10957/PS2

DOI: 10.1023/A:1022664513146

Access Statistics for this article

Journal of Optimization Theory and Applications is currently edited by Franco Giannessi and David G. Hull

More articles in Journal of Optimization Theory and Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().