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...
We introduce some new models of infinite-state transition systems. The basic model, called a (reversal-bounded) counter machine (CM), is a nondeterministic finite automaton augment...
— One feature that classification algorithms typically lack is the ability to know what they do not know. With this knowledge an algorithm would be able to operate in any domain...
Range searching is a well known problem in the area of geometric data structures. We consider this problem in the context of approximation, where an approximation parameter ε >...
The Hierarchical Mixture of Experts (HME) is a well-known tree-structured model for regression and classification, based on soft probabilistic splits of the input space. In its o...