Poster
Independence Testing for Bounded Degree Bayesian Networks
Arnab Bhattacharyya · Clément L Canonne · Qiping Yang
Hall J (level 1) #818
Keywords: [ Probabilistic Graphical Model ] [ bayesian network ] [ distribution testing ]
Abstract:
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 ε-far in total variation distance from any product distribution. For arbitrary distributions, this problem requires exp(n) samples. We show in this work that if P has a sparse structure, then in fact only linearly many samples are required.Specifically, if P is Markov with respect to a Bayesian network whose underlying DAG has in-degree bounded by d, then ˜Θ(2d/2⋅n/ε2) samples are necessary and sufficient for independence testing.
Chat is not available.