Robust Learning of Fixed-Structure Bayesian Networks in Nearly-Linear Time

Yu Cheng, Honghao Lin

Keywords: Bayesian networks, robust statistics, learning theory

Abstract:

We study the problem of learning Bayesian networks where an $\epsilon$-fraction of the samples are adversarially corrupted. We focus on the fully-observable case where the underlying graph structure is known. In this work, we present the first nearly-linear time algorithm for this problem with a dimension-independent error guarantee. Previous robust algorithms with comparable error guarantees are slower by at least a factor of $(d/\epsilon)$, where $d$ is the number of variables in the Bayesian network and $\epsilon$ is the fraction of corrupted samples.

Our algorithm and analysis are considerably simpler than those in previous work. We achieve this by establishing a direct connection between robust learning of Bayesian networks and robust mean estimation. As a subroutine in our algorithm, we develop a robust mean estimation algorithm whose runtime is nearly-linear in the number of nonzeros in the input samples, which may be of independent interest.

One-sentence Summary: We give the first nearly-linear time algorithm for the robust learning of fixed-structure Bayesian networks.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Code: [ chycharlie/robust-bn-faster](https://github.com/chycharlie/robust-bn-faster)