We study the computational and sample complexity of parameter and structure learning in graphical models. Our main result shows that the class of factor graphs with bounded degree...
The MAP (maximum a posteriori hypothesis) problem in Bayesian networks is to find the most likely states of a set of variables given partial evidence on the complement of that set...
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Deep belief networks are a powerful way to model complex probability distributions. However, it is difficult to learn the structure of a belief network, particularly one with hidd...
Ryan Prescott Adams, Hanna M. Wallach, Zoubin Ghah...
Text clustering is most commonly treated as a fully automated task without user supervision. However, we can improve clustering performance using supervision in the form of pairwi...