`

Timezone: »

 
Poster
Learning Bayesian Networks with Low Rank Conditional Probability Tables
Adarsh Barik · Jean Honorio

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #223
in Theory -- Learning Theory »

In this paper, we provide a method to learn the directed structure of a Bayesian network using data. The data is accessed by making conditional probability queries to a black-box model. We introduce a notion of simplicity of representation of conditional probability tables for the nodes in the Bayesian network, that we call `low rankness''. We connect this notion to the Fourier transformation of real valued set functions and propose a method which learns the exact directed structure of alow rank` Bayesian network using very few queries. We formally prove that our method correctly recovers the true directed structure, runs in polynomial time and only needs polynomial samples with respect to the number of nodes. We also provide further improvements in efficiency if we have access to some observational data.

Keywords: Learning Theory · Theory
[ Paper]  [ Poster] 

Author Information

Adarsh Barik (Purdue University)
Jean Honorio (Purdue University)

More from the Same Authors