A new "herding" algorithm is proposed which directly converts observed moments into a sequence of pseudo-samples. The pseudosamples respect the moment constraints and ma...
We describe a model of document citation that learns to identify hubs and authorities in a set of linked documents, such as pages retrieved from the world wide web, or papers retr...
In this paper we describe the e-LD approach for the design and repurposing of Units of Learning (UoLs). This approach is centered in domain-specific Educational Modeling Languages...
We consider three natural models of random logarithmic depth decision trees over Boolean variables. We give an efficient algorithm that for each of these models learns all but an ...
We empirically evaluate several state-of-theart methods for constructing ensembles of heterogeneous classifiers with stacking and show that they perform (at best) comparably to se...