We study the problem of learning a group of principal tasks using a group of auxiliary tasks, unrelated to the principal ones. In many applications, joint learning of unrelated ta...
Bernardino Romera-Paredes, Andreas Argyriou, Nadia...
We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample d...
Ruslan Salakhutdinov, Sham M. Kakade, Dean P. Fost...
To relax the homogeneity assumption of classical dynamic Bayesian networks (DBNs), various recent studies have combined DBNs with multiple changepoint processes. The underlying as...
We propose a new family of latent variable models called max-margin min-entropy (m3e) models, which define a distribution over the output and the hidden variables conditioned on ...
Kevin Miller, M. Pawan Kumar, Benjamin Packer, Dan...
Abstract. Database modeling is based on the assumption of a high regularity of its application areas, an assumption which applies to both the structure of data and the behavior of ...
Hans-Werner Sehring, Sebastian Bossung, Joachim W....