Goto

Collaborating Authors

 alphabet



Efficient Gradient Computation for Structured Output Learning with Rational and Tropical Losses

Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Dmitry Storcheus, Scott Yang

Neural Information Processing Systems

Many of these algorithms have been successfully used with specific loss functions such as the Hamming loss. Their use has been also extended to multivariate performance measures such as Precision/Recall orF1-score (Joachims,2005),which depend onpredictions onalltraining points.








Supplementary S.1 NetworkDetails

Neural Information Processing Systems

More specifically, one lossisLalpha = C 1 thatencourages aminimal alpha mask butmight result inagrainymask, so the other loss isLdiv = d, i.e., minimizing the divergence of the distance field to achieve more smooth/continuous alphamask.