In many structured prediction problems, the highest-scoring labeling is hard to compute exactly, leading to the use of approximate inference methods. However, when inference is us...
We propose a conservative extension of HM(X), a generic constraint-based type inference framework, with bounded existential (a.k.a. abstract) and universal (a.k.a. polymorphic) da...
Abstract. This paper proposes to promote constraints to first-class status. In contrast to constraint propagation, which performs inference on values of variables, first-class co...
In this paper, we describe the threats to privacy that can occur through data mining and then view the privacy problem as a variation of the inference problem in databases. Keywor...
We study the problem of combining the outcomes of several different classifiers in a way that provides a coherent inference that satisfies some constraints. In particular, we deve...