Year: 2007
Type: book-chapter
Abstract: The risk, or probability of error, of the classifier produced by the AdaBoost algorithm is investigated. In particular, we consider the stopping strategy to be used in AdaBoost to achieve universal consistency. We show that provided AdaBoost is stopped after $n^{1-\\varepsilon}$ iterations---for sample size $n$ and $\\varepsilon \\in (0,1)$---the sequence of risks of the classifiers it produces approaches the Bayes risk.
Source: The MIT Press eBooks
Authors: Peter L. Bartlett, Mikhail Traskin
Institution: University of California, Berkeley
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: National Science Foundation
OpenAlex ID: W2102281237