Independence Testing for Bounded Degree Bayesian Networks

Authors: Arnab Bhattacharyya, Clément L Canonne, Qiping Yang

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We study the following independence testing problem: given access to samples from a distribution P over {0, 1}n, decide whether P is a product distribution or whether it is "-far in total variation distance from any product distribution. ... Our main result essentially settles this question, and establishes the following: Theorem 1.1 (Informal Main Theorem). ... In the course of proving this theorem, we additionally derive several technical results that are of independent interest, such as bounds on the moment generating function of squared binomials and an independence testing algorithm for arbitrary distributions in Hellinger distance.
Researcher Affiliation Academia Arnab Bhattacharyya School of Computing National University of Singapore arnabb@nus.edu.sg Clement L. Canonne School of Computer Science University of Sydney clement.canonne@sydney.edu.au Joy Qiping Yang School of Computing National University of Singapore joy.yang@nus.edu.sg
Pseudocode Yes Algorithm 1: Independence testing for degree-d Bayes net ... Algorithm 2: Hellinger independence testing for general distributions
Open Source Code No The paper does not provide any statements or links indicating that source code for the described methodology is publicly available.
Open Datasets No This paper is theoretical and focuses on sample complexity for distribution testing. It does not use real-world datasets for training or evaluation. Therefore, no information about publicly available datasets is provided.
Dataset Splits No The paper is theoretical and does not involve empirical experiments with data splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe running empirical experiments, so it does not mention any hardware specifications.
Software Dependencies No The paper is theoretical and focuses on algorithms and proofs. It does not mention any specific software dependencies with version numbers that would be needed for implementation or reproduction of experimental results.
Experiment Setup No The paper is theoretical and does not describe empirical experiments. Therefore, it does not provide details on experimental setup such as hyperparameters or training configurations.