Cutting Plane MAP Inference for Markov Logic
نویسنده
چکیده
In this work we present Cutting Plane Inference (CPI) for MAP inference in Markov Logic. CPI incrementally solves partial Ground Markov Networks, adding formulae only if they are violated in the current solution. We show dramatic improvements in terms of e ciency, and discuss scenarios where CPI is likely to be fast.
منابع مشابه
Improving the Accuracy and Efficiency of MAP Inference for Markov Logic
In this work we present Cutting Plane Inference (CPI), a Maximum A Posteriori (MAP) inference method for Statistical Relational Learning. Framed in terms of Markov Logic and inspired by the Cutting Plane Method, it can be seen as a meta algorithm that instantiates small parts of a large and complex Markov Network and then solves these using a conventional MAP method. We evaluate CPI on two task...
متن کاملEfficient maximum a-posteriori inference in Markov logic and application in description logics
The maximum a-posteriori (MAP) query in statistical relational models computes the most probable world given evidence and further knowledge about the domain. It is arguably one of the most important types of computational problems, since it is also used as a subroutine in weight learning algorithms. In this thesis, we discuss an improved inference algorithm and an application for MAP queries. W...
متن کاملRockIt: Exploiting Parallelism and Symmetry for MAP Inference in Statistical Relational Models
ROCKIT is a maximum a-posteriori (MAP) query engine for statistical relational models. MAP inference in graphical models is an optimization problem which can be compiled to integer linear programs (ILPs). We describe several advances in translating MAP queries to ILP instances and present the novel meta-algorithm cutting plane aggregation (CPA). CPA exploits local context-specific symmetries an...
متن کاملProbabilistic EL with Nominals and Concrete Domains
We present MEL (M denotes Markov logic networks) an extension of the log-linear description logics EL-LL with concrete domains, nominals, and instances. We use Markov logic networks (MLNs) in order to find the most probable, classified and coherent EL ontology from anMEL knowledge base. In particular, we develop a novel way to deal with concrete domains by extending MLN’s cutting plane inferenc...
متن کاملFocused Grounding for Markov Logic Networks
Markov logic networks have been successfully applied to many problems in AI. However, the computational complexity of the inference procedures has limited their application. Previous work in lifted inference, lazy inference and cutting plane inference has identified cases where the entire ground network need not be constructed. These approaches are specific to particular inference procedures, a...
متن کامل