Learning causal Bayes networks using interventional path queries in polynomial time and sample complexity

06/02/2017
by   Kevin Bello, et al.
0

Causal discovery from empirical data is a fundamental problem in many scientific domains. Observational data allows for identifiability only up to Markov equivalence class. In this paper, we propose a polynomial time algorithm for learning the exact correctly-oriented structure of the transitive reduction of any causal Bayesian networks with high probability, by using interventional path queries. Each path query takes as input an origin node and a target node, and answers whether there is a directed path from the origin to the target. This is done by intervening the origin node and observing samples from the target node. We theoretically show the logarithmic sample complexity for the size of interventional data per path query, for continuous and discrete networks. We extent our work by presenting how to learn the transitive edges using logarithmic sample complexity (albeit in time exponential in the maximum number of parents for discrete networks) and by providing an analysis of imperfect interventions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/03/2017

Learning Identifiable Gaussian Bayesian Networks in Polynomial Time and Sample Complexity

Learning the directed acyclic graph (DAG) structure of a Bayesian networ...
research
07/04/2012

Learning Factor Graphs in Polynomial Time & Sample Complexity

We study computational and sample complexity of parameter and structure ...
research
03/12/2018

Learning Binary Bayesian Networks in Polynomial Time and Sample Complexity

We consider the problem of structure learning for binary Bayesian networ...
research
08/08/2022

Exact Learning of Multitrees and Almost-Trees Using Path Queries

Given a directed graph, G=(V,E), a path query, path(u,v), returns whethe...
research
03/21/2019

Learning Two layer Networks with Multinomial Activation and High Thresholds

Giving provable guarantees for learning neural networks is a core challe...
research
01/10/2019

On the Distance Between the Rumor Source and Its Optimal Estimate on a Regular Tree

This paper addresses the rumor source identification problem, where the ...
research
01/10/2019

On the Distance Between the Rumor Source and Its Optimal Estimate in a Regular Tree

This paper addresses the rumor source identification problem, where the ...

Please sign up or login with your details

Forgot password? Click here to reset