Sciweavers

Share
NIPS
2004

Breaking SVM Complexity with Cross-Training

9 years 22 days ago
Breaking SVM Complexity with Cross-Training
We propose to selectively remove examples from the training set using probabilistic estimates related to editing algorithms (Devijver and Kittler, 1982). This heuristic procedure aims at creating a separable distribution of training examples with minimal impact on the position of the decision boundary. It breaks the linear dependency between the number of SVs and the number of training examples, and sharply reduces the complexity of SVMs during both the training and prediction stages.
Gökhan H. Bakir, Léon Bottou, Jason We
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2004
Where NIPS
Authors Gökhan H. Bakir, Léon Bottou, Jason Weston
Comments (0)
books