Solving All Regression Models For Learning Gaussian Networks Using Givens Rotations

TL;DR

This paper introduces an efficient algorithm using Givens rotations and QR decompositions to compute all regression models needed for score-based learning of Gaussian Bayesian networks, significantly reducing computational complexity.

Contribution

The paper presents a novel algorithm that efficiently computes all regressions for Bayesian network learning using Givens rotations, outperforming existing methods in complexity.

Findings

The proposed algorithm has the lowest complexity among compared methods.

It enables exact and efficient computation of all regression models.

Parallelization further reduces runtime proportionally to processor count.

Abstract

Score based learning (SBL) is a promising approach for learning Bayesian networks. The initial step in the majority of the SBL algorithms consists of computing the scores of all possible child and parent-set combinations for the variables. For Bayesian networks with continuous variables, a particular score is usually calculated as a function of the regression of the child over the variables in the parent-set. The sheer number of regressions models to be solved necessitates the design of efficient numerical algorithms. In this paper, we propose an algorithm for an efficient and exact calculation of regressions for all child and parent-set combinations. In the proposed algorithm, we use QR decompositions (QRDs) to capture the dependencies between the regressions for different families and Givens rotations to efficiently traverse through the space of QRDs such that all the regression models are accounted for in the shortest path possible. We compare the complexity of the suggested method with different algorithms, mainly those arising in all subset regression problems, and show that our algorithm has the smallest algorithmic complexity. We also explain how to parallelize the proposed method so as to decrease the runtime by a factor proportional to the number of processors utilized.