![A Support Vector Method for Multivariate Performance Measures thumbnail](https://apiminio.videolectures.net/vln/lectures/2438/1/en/thumbnail.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=masoud%2F20241217%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20241217T010207Z&X-Amz-Expires=604800&X-Amz-SignedHeaders=host&X-Amz-Signature=22eeaa512aabfc078264a7895164f58825f493303f74b70997b54724bdf407dc)
A Support Vector Method for Multivariate Performance Measures
Published on Apr 12, 20076652 Views
We examine the relationship between the predictions made by different learning algorithms and true posterior probabilities. We show that maximum margin methods such as boosted trees and boosted st