Linear classifiers are nearly optimal when hidden variables have diverse effects (Q420914): Difference between revisions
From MaRDI portal
Added link to MaRDI item. |
Changed an Item |
||
Property / describes a project that uses | |||
Property / describes a project that uses: Pegasos / rank | |||
Normal rank |
Revision as of 07:50, 28 February 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Linear classifiers are nearly optimal when hidden variables have diverse effects |
scientific article |
Statements
Linear classifiers are nearly optimal when hidden variables have diverse effects (English)
0 references
23 May 2012
0 references
In this paper the authors focus on showing that a linear classifier can provide a good approximation even if the optimal classifier is much more complex. To prove this hypothesis, they analyze a classification problem in which data is generated by a two-tiered random process. Concretely, they prove that, if the hidden variables have non-eligible effects on many observed variables, a linear classifier accurately approximates the error rate of the optimal classifier (Bayes). Moreover, the hinge loss of the linear classifier is not much more than the Bayes error rate.
0 references
learning theory
0 references
Bayes optimal rule
0 references
linear classification
0 references
hidden variables
0 references