A hybrid loss for multiclass and structured prediction
We propose a novel hybrid loss for multiclass and structured prediction problems that is a convex combination of a log loss for Conditional Random Fields (CRFs) and a multiclass hinge loss for Support Vector Machines (SVMs). We provide a sufficient condition for when the hybrid loss is Fisher consistent for classification. This condition depends on a measure of dominance between labels - specifically, the gap between the probabilities of the best label and the second best label. We also prove...[Show more]
|Collections||ANU Research Publications|
|Source:||IEEE Transactions on Pattern Analysis and Machine Intelligence|
|01_Shi_A_hybrid_loss_for_multiclass_2015.pdf||889.67 kB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.