Soundness and coercion resistance are the important and intricate security requirements for remote voting protocols. Several formal models of soundness and coercion-resistance hav...
We derive PAC-Bayesian generalization bounds for supervised and unsupervised learning models based on clustering, such as co-clustering, matrix tri-factorization, graphical models...
We study losses for binary classification and class probability estimation and extend the understanding of them from margin losses to general composite losses which are the compos...
This work deals with four classical prediction settings, namely full information, bandit, label efficient and bandit label efficient as well as four different notions of regret: p...
Subgroup discovery aims at finding subsets of a population whose class distribution is significantly different from the overall distribution. A number of multi-class subgroup disc...