@inproceedings{abc886988d5f489e9e2d394440804406,
title = "Discovering Reliable Dependencies from Data: Hardness and Improved Algorithms",
abstract = "The reliable fraction of information is an attractive score for quantifying (functional) dependencies in high-dimensional data. In this paper, we systematically explore the algorithmic implications of using this measure for optimization. We show that the problem is NP-hard, which justifies the usage of worst-case exponential-time as well as heuristic search methods. We then substantially improve the practical performance for both optimization styles by deriving a novel admissible bounding function that has an unbounded potential for additional pruning over the previously proposed one. Finally, we empirically investigate the approximation ratio of the greedy algorithm and show that it produces highly competitive results in a fraction of time needed for complete branch-and-bound style search.",
keywords = "Approximate functional dependency, Branch-and-bound, Information theory, Knowledge discovery, Optimization",
author = "Panagiotis Mandros and Mario Boley and Jilles Vreeken",
note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 18th IEEE International Conference on Data Mining, ICDM 2018 ; Conference date: 17-11-2018 Through 20-11-2018",
year = "2018",
month = dec,
day = "27",
doi = "https://doi.org/10.1109/ICDM.2018.00047",
language = "American English",
series = "Proceedings - IEEE International Conference on Data Mining, ICDM",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "317--326",
booktitle = "2018 IEEE International Conference on Data Mining, ICDM 2018",
address = "United States",
}