Dealing with a large number of classes -- Likelihood, Discrimination or Ranking?

06/22/2016

∙

by   David Barber, et al.

∙

0

∙

share

We consider training probabilistic classifiers in the case of a large number of classes. The number of classes is assumed too large to perform exact normalisation over all classes. To account for this we consider a simple approach that directly approximates the likelihood. We show that this simple approach works well on toy problems and is competitive with recently introduced alternative non-likelihood based approximations. Furthermore, we relate this approach to a simple ranking objective. This leads us to suggest a specific setting for the optimal threshold in the ranking objective.