Knowledge Compilation with Continuous Random Variables and its Application in Hybrid Probabilistic Logic Programming

In probabilistic reasoning, the traditionally discrete domain has been elevated to the hybrid domain encompassing additionally continuous random variables. Inference in the hybrid domain, however, usually necessitates to condone trade-offs on either the inference on discrete or continuous random variables. We introduce a novel approach based on weighted model integration and algebraic model counting that circumvents these trade-offs. We then show how it supports knowledge compilation and exact probabilistic inference. Moreover, we introduce the hybrid probabilistic logic programming language HAL-ProbLog, an extension of ProbLog, to which we apply our inference approach.

[1]  Adnan Darwiche,et al.  On probabilistic inference by weighted model counting , 2008, Artif. Intell..

[2]  Peter J. F. Lucas,et al.  Approximate Probabilistic Inference with Bounded Error for Hybrid Probabilistic Logic Programming , 2016, IJCAI.

[3]  Luc De Raedt,et al.  Extending ProbLog with Continuous Distributions , 2010, ILP.

[4]  Luc De Raedt,et al.  Probabilistic logic programming for hybrid relational domains , 2016, Machine Learning.

[5]  Chung-Kil Hur,et al.  R2: An Efficient MCMC Sampler for Probabilistic Programs , 2014, AAAI.

[6]  Timon Gehr,et al.  PSI: Exact Symbolic Inference for Probabilistic Programs , 2016, CAV.

[7]  Luc De Raedt,et al.  Algebraic model counting , 2012, J. Appl. Log..

[8]  Pierre Marquis,et al.  A Knowledge Compilation Map , 2002, J. Artif. Intell. Res..

[9]  Guy Van den Broeck,et al.  Component Caching in Hybrid Domains with Piecewise Polynomial Densities , 2016, AAAI.

[10]  Luc De Raedt,et al.  Inference and learning in probabilistic logic programs using weighted Boolean formulas , 2013, Theory and Practice of Logic Programming.

[11]  Luc De Raedt,et al.  An Algebraic Prolog for Reasoning about Possible Worlds , 2011, AAAI.

[12]  Adnan Darwiche,et al.  Dynamic Minimization of Sentential Decision Diagrams , 2013, AAAI.

[13]  Taisuke Sato,et al.  A Statistical Learning Method for Logic Programs with Distribution Semantics , 1995, ICLP.

[14]  C. R. Ramakrishnan,et al.  Inference in probabilistic logic programs with continuous random variables , 2011, Theory and Practice of Logic Programming.

[15]  Luc De Raedt,et al.  ProbLog2: Probabilistic Logic Programming , 2015, ECML/PKDD.

[16]  Adnan Darwiche,et al.  Compiling Probabilistic Graphical Models Using Sentential Decision Diagrams , 2013, ECSQARU.

[17]  Andrea Passerini,et al.  Efficient Weighted Model Integration via SMT-Based Predicate Abstraction , 2017, IJCAI.

[18]  Luc De Raedt,et al.  Under Consideration for Publication in Theory and Practice of Logic Programming the Magic of Logical Inference in Probabilistic Programming , 2022 .

[19]  Stuart J. Russell,et al.  BLOG: Probabilistic Models with Unknown Objects , 2005, IJCAI.

[20]  Luc De Raedt,et al.  TP-Compilation for inference in probabilistic logic programs , 2016, Int. J. Approx. Reason..

[21]  Peter J. F. Lucas,et al.  Modeling the Interactions between Discrete and Continuous Causal Factors in Bayesian Networks , 2015, Int. J. Intell. Syst..

[22]  Guy Van den Broeck,et al.  Probabilistic Inference in Hybrid Domains by Weighted Model Integration , 2015, IJCAI.