Highly Influential

- Published 2014 in Annals of Mathematics and Artificial Intelligence
DOI:10.1007/s10472-015-9465-7

In the standard agnostic multiclass model, <instance, label > pairs are sampled independently from some underlying distribution. This distribution induces a conditional probability over the labels given an instance, and our goal in this paper is to learn this conditional distribution. Since even unconditional densities are quite challenging to learn, we… (More)

### Presentations referencing similar topics