We address the problem of learning the parameters in graphical models when inference is intractable. A common strategy in this case is to replace the partition function with its B...
We introduce a simple aggregate claims model, which is able to take into account a continuous range of positive dependence between independence and comonotone dependence. It is ba...
Design for specific customer service plays a crucial role for the majority of the market in modern electronics. However, adaptability to an individual customer results in increasi...
In this paper, we present an overview of generalized expectation criteria (GE), a simple, robust, scalable method for semi-supervised training using weakly-labeled data. GE fits m...
We present a genetic model based on simulated recombination of fixed sequences of quaternary genes (assuming four distinct forms, or alleles). States and dynamics of the infinite ...