Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss
applied to the outputs of a neural network, when the softmax is used. But, what guarantees …

Ranking has been extensively studied in information retrieval, machine learning and
statistics. A central problem in ranking is to design a ranking measure for evaluation of …

The objective in extreme multi-label classification is to learn a classifier that can
automatically tag a data point with the most relevant subset of labels from a large label set …

A series of recent publications by Awasthi et al. have introduced the key notion of* $ H $-
consistency bounds* for surrogate loss functions. These are upper bounds on the zero-one …

We present an extensive study of $ H $-consistency bounds for multi-class classification.
These are upper bounds on the target loss estimation error of a predictor in a hypothesis set …

We consider the problem of generating rankings that are fair towards both users and item
producers in recommender systems. We address both usual recommendation (eg, of music …

We present a detailed study of $ H $-consistency bounds for score-based ranking. These
are upper bounds on the target loss estimation error of a predictor in a hypothesis set $ H …

Over the past decades, numerous loss functions have been been proposed for a variety of
supervised learning tasks, including regression, classification, ranking, and more generally …

We introduce a novel framework of ranking with abstention, where the learner can abstain
from making prediction at some limited cost $ c $. We present a extensive theoretical …

Learning to rank is an increasingly important scientific field that comprises the use of
machine learning for the ranking task. New learning to rank methods are generally …