Corruption is frequently observed in collected data and has been extensi...
We argue that insurance can act as an analogon for the social situatedne...
Mixable loss functions are of fundamental importance in the context of
p...
Probabilistic predictions can be evaluated through comparisons with obse...
In literature on imprecise probability little attention is paid to the f...
Strict frequentism defines probability as the limiting relative frequenc...
Statistical decision problems are the foundation of statistical machine
...
Expected risk minimization (ERM) is at the core of machine learning syst...
Fair Machine Learning endeavors to prevent unfairness arising in the con...
We introduce two new classes of measures of information for statistical
...
Machine learning typically presupposes classical probability theory whic...
A landmark negative result of Long and Servedio established a worst-case...
Conditional Value at Risk (CVaR) is a family of "coherent risk measures"...
The study of a machine learning problem is in many ways is difficult to
...
Since the introduction of Generative Adversarial Networks (GANs) and
Var...
Ensuring that classifiers are non-discriminatory or fair with respect to...
The goal of online prediction with expert advice is to find a decision
s...
The cost-sensitive classification problem plays a crucial role in
missio...
We consider the setting of prediction with expert advice; a learner make...
We consider the setting of prediction with expert advice; a learner make...
Nowozin et al showed last year how to extend the GAN
principle to all f-...
The speed with which a learning algorithm converges as it is presented w...
Many classification algorithms produce a classifier that is a weighted
a...
In supervised learning one wishes to identify a pattern present in a joi...
Feature Learning aims to extract relevant information contained in data ...
Mixability of a loss is known to characterise when constant regret bound...
"Deep Learning" methods attempt to learn generic features in an unsuperv...
We study losses for binary classification and class probability estimati...