Overview:

Regular probabilistic inference algorithms operate on the propositional level (as opposed to first-order level when there is a notion of multiple objects). Some languages exist for specifying probabilistic knowledge in a first-order level, but the inference still remains on a mostly propositional level.

We seek to provide a lifted first-order probabilistic inference algorithm that performs at a first-order level even during inference itself, and not only at the specification stage. The benefits of such an algorithm are improved efficiency and greater comprehensibility of inference steps (which are more like a proof tree).

Collaborations: