• GpuBE : This code implements an inference-based algorithm which exploits Graphical Processing Units (GPUs) to speed up the resolution of exact and approximated inference-based algorithms for discrete optimization (e.g., WCSPs). For details, please refer to the original paper. Ferdinando Fioretto, Enrico Pontelli, William Yeoh, and Rina Dechter Accelerating Exact and Approximate Inference for (Distributed) Discrete Optimization with GPUs, CoRR abs/1608.05288 (2016).

  • Merlin : Merlin is an extensible C++ library that implements state-of-the-art exact and approximate algorithms for probabilistic inference over graphical models including both directed and undirected models (e.g., Bayesian networks, Markov Random Fields). It can be used for many applications and research in bioinformatics, computer vision, or speech and language processing to name a few. Merlin supports the most common probabilistic inference tasks such as computing the partition function or probability of evidence (PR), posterior marginals (MAP), as well as MAP (also known as maximum aposteriori or most probable explanation) and marginal MAP configurations. By Radu Marinescu, IBM Research Ireland.

  • Daoopt : DAOOPT: Distributed AND/OR Optimization An implementation of sequential as well as distributed AND/OR Branch-and-Bound and its Breadth-Rotating AND/OR Branch-and-Bound enhancement for combinatorial optimization problems expressed as MPE (max-product) queries over graphical models like Bayes and Markov networks. By Lars Otten, University of California, Irvine.

    Also see Daoopt-Exp for a branch of the above that implements various dynamic heuristics such as factor graph linear programming and lookahead search. This also implements AND/OR Best-First Search with heuristics for subproblem ordering. By William Lam, University of California, Irvine.

  • AOMDD: AOMDD: AND/OR Multivalued Decision Diagrams. A base implementation of AOMDDs, including operations to combine diagrams with an "Apply" operator. Also contains an implementation of bucket elimination using AOMDDs that enable exact inference on problems with high treewidth. By William Lam, University of California, Irvine.

  • IJGP-Sampling-SampleSearch : IJGP-Sampling-SampleSearch. By Vibhav Gogate.

  • SampleSearch for Counting, IJGP for MAR, QuickBB : SampleSearch for approximate counting task, IJGP for MAR task, and QuickBB for computing the treewidth of a graph. By Vibhav Gogate.

  • REES : Reasoning Engine(s) Evaluation Shell. By Radu Marinescu, Kalev Kask and Rina Dechter

  • DIS : Dynamic Importance Sampling for Anytime Bounds of the Partition Function. By Qi Lou, Rina Dechter, and Alexander Ihler. Published at NIPS-17.

  • pyGM : Python Toolbox for Graphical Models. By Alexander Iher.

  • gmid : Code for papers published at UAI 2018/2019/SocS2020. By Junkyu Lee.

  • gmid2 : Code for submodel decomposition for influence diagrams. By Junkyu Lee.