An Integer Polynomial Programming Based Framework for Lifted MAP Inference

Authors: Somdeb Sarkhel, Deepak Venugopal, Parag Singla, Vibhav G Gogate

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on several benchmark MLNs show that our new algorithm is substantially superior to ground inference and existing methods in terms of computational efficiency and solution quality.
Researcher Affiliation Academia Somdeb Sarkhel, Deepak Venugopal Computer Science Department The University of Texas at Dallas {sxs104721,dxv021000}@utdallas.edu Parag Singla Department of CSE I.I.T. Delhi parags@cse.iitd.ac.in Vibhav Gogate Computer Science Department The University of Texas at Dallas vgogate@hlt.utdallas.edu
Pseudocode Yes Algorithm 1 PTP-MAP(MLN M)... Algorithm 2 SMLN-2-IPP(SMLN S)
Open Source Code No The paper mentions using open-source software (Alchemy, Tuffy) and a commercial solver (Gurobi), but does not state that the code for their own proposed methodology is open source or publicly available.
Open Datasets Yes (iii) Citation Information-Extraction (IE) MLN [11] from the Alchemy web page, consisting of five predicates and fourteen formulas.
Dataset Splits No The paper does not provide specific dataset split information (e.g., percentages, sample counts, or detailed splitting methodology) for training, validation, or test sets.
Hardware Specification Yes All our experiments were run on a third generation i7 quad-core machine having 8GB RAM.
Software Dependencies No The paper mentions software like Gurobi, Alchemy, and Tuffy but does not specify their version numbers.
Experiment Setup No The paper describes the MLNs used for evaluation and the metrics recorded (solution quality vs. time), but it does not provide specific experimental setup details such as hyperparameters or specific training configurations for the models or algorithms beyond what is implied by the core problem (MAP inference).