Active Learning of Continuous-time Bayesian Networks through Interventions

Authors: Dominik Linzner, Heinz Koeppl

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the performance of our criterion on synthetic and realworld data.
Researcher Affiliation Collaboration Dominik Linzner 1 2 Heinz Koeppl 1 3... 1Department of Engineering and Information Technology, TU Darmstadt, Germany 2The Why Company Gmb H, Berlin, Germany 3Department of Biology, TU Darmstadt, Germany.
Pseudocode Yes Appendix A: Algorithm 1: (V)BHC driven experimental design
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes We apply our method to the British Household Panel Survey (BHPS) (on Micro-social Change, 2003). This data-set has been collected yearly from 1991 to 2002, thus consisting of 11 time-points.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions "standard Matlab optimizers" but does not provide specific version numbers for Matlab or any other software dependencies needed to replicate the experiment.
Experiment Setup Yes We set NS = 10 and the length of each trajectory fixed to be τ = 3 a.u.