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

arXiv: https://arxiv.org/abs/1606.06959 · HTML: https://mlsanity.com/paper/1606.06959/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2016.

## Built on by (most cited first, 1 of 1)

- [S-Rocket: Selective Random Convolution Kernels for Time Series Classification](https://mlsanity.com/paper/2203.03445/) (2022)

## Abstract (arXiv)

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.