# Discovering Reliable Dependencies from Data: Hardness and Improved Algorithms

arXiv: https://arxiv.org/abs/1809.05467 · HTML: https://mlsanity.com/paper/1809.05467/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2018.

## Built on by (most cited first, 1 of 1)

- [Information efficient learning of complexly structured preferences: Elicitation procedures and their application to decision making under uncertainty](https://mlsanity.com/paper/2110.12879/) (2021)

## Abstract (arXiv)

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.