The Pessimistic Limits of Margin-based Losses in Semi-supervised Learning

12/28/2016

∙

by   Jesse H. Krijthe, et al.

∙

0

∙

share

We show that for linear classifiers defined by convex margin-based surrogate losses that are monotonically decreasing, it is impossible to construct any semi-supervised approach that is able to guarantee an improvement over the supervised classifier measured by this surrogate loss. For non-monotonically decreasing loss functions, we demonstrate safe improvements are possible.