reproducibilityindex.ai

Finding an ϵ-Close Minimal Variation of Parameters in Bayesian Networks

Authors: Bahare Salmani, Joost-Pieter Katoen

Reproducibility Variable	Result	LLM Response
Research Type	Experimental	Our experiments show that ϵ-close tuning of large BN benchmarks with up to eight parameters is feasible.Our experiments on our prototypical implementation indicate that ϵ-bounded tuning of up to 8 parameters for large networks with 100 variables is feasible.
Researcher Affiliation	Academia	Bahare Salmani and Joost-Pieter Katoen RWTH Aachen University {salmani, katoen}@cs.rwth-aachen.de
Pseudocode	Yes	Algorithm 1: Minimal change tuning" and "Algorithm 2: R+-minimal distance instantiation
Open Source Code	Yes	1https://github.com/baharslmn/pbn-epsilon-tuning
Open Datasets	Yes	We parametrized benchmarks from bnlearn repository and deﬁned different constraints.
Dataset Splits	No	The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology).
Hardware Specification	Yes	We conducted all our experiments on a 2.3 GHz Intel Core i5 processor with 16 GB RAM.
Software Dependencies	Yes	We empirically evaluated our approach using a prototypical realization on top of the probabilistic model checker Storm [Hensel et al., 2022] (version 1.7.0).
Experiment Setup	Yes	The hyperparameters of the algorithm are the coverage factor 0 < η < 1, the region expansion factor 0 < γ < 1, and the maximum number of iterations K N.We took γ=1/2 and K=6 for our experiments, see Sec. 5.4.