2015/07/10 by James Cussens, Cussens, James
Computer Science · Mathematics · #AI-based Problem Solving and Planning #Algorithm #Artificial Intelligence (cs.AI) #Bayesian Modeling and Causal Inference #Business #Computer science #FOS: Computer and information sciences #Integer (computer science) #Integer programming #Machine Learning and Algorithms #Mathematics #Order (exchange) #Programming language #cs.AI
paper · pdf · doi:10.48550/arxiv.1507.02912
corrected typos
openalex publication_date 2015/07/10 · arxiv created 2015/07/13 · arxiv updated 2015/07/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
Finding the most probable (MAP) model in SRL frameworks such as Markov logic and Problog can, in principle, be solved by encoding the problem as a `grounded-out' mixed integer program (MIP). However, useful first-order structure disappears in this process motivating the development of first-order MIP approaches. Here we present mfoilp, one such approach. Since the syntax and semantics of mfoilp is essentially the same as existing approaches we focus here mainly on implementation and algorithmic issues. We start with the (conceptually) simple problem of using a logic program to generate a MIP instance before considering more ambitious exploitation of first-order representations.