Exact estimation of multiple directed acyclic graphs

Chris J. Oates; Jim Q. Smith; Sach Mukherjee; James Cussens

doi:10.1007/s11222-015-9570-9

Exact estimation of multiple directed acyclic graphs

Chris J. Oates^*
, Jim Q. Smith
, Sach Mukherjee
, James Cussens

^*Corresponding author for this work

Research output: Contribution to journal › Article (Academic Journal) › peer-review

24 Citations (Scopus)

Abstract

This paper considers structure learning for multiple related directed acyclic graph (DAG) models. Building on recent developments in exact estimation of DAGs using integer linear programming (ILP), we present an ILP approach for joint estimation over multiple DAGs. Unlike previous work, we do not require that the vertices in each DAG share a common ordering. Furthermore, we allow for (potentially unknown) dependency structure between the DAGs. Results are presented on both simulated data and fMRI data obtained from multiple subjects.

Original language	English
Pages (from-to)	797–811
Number of pages	15
Journal	Statistics and Computing
Volume	26
Early online date	19 Jun 2015
DOIs	https://doi.org/10.1007/s11222-015-9570-9
Publication status	Published - 1 Jul 2016

Bibliographical note

Funding Information:
CJO was supported by the Centre for Research in Statistical Methodology (CRiSM) EPSRC EP /D002060/1. JC was supported by the Medical Research Council (Project Grant G1002312). SM was supported by the UK Medical Research Council and is a recipient of a Royal Society Wolfson Research Merit Award.

Publisher Copyright:
© Springer Science+Business Media New York 2015.

Keywords

Hierarchical model
Bayesian network
Multiregression dynamical model
Integer linear programming
Joint estimation

Access to Document

10.1007/s11222-015-9570-9

Handle.net

Persistent link

Cite this

@article{5920533353d7448ca13943f5fd3c9c8e,

title = "Exact estimation of multiple directed acyclic graphs",

abstract = "This paper considers structure learning for multiple related directed acyclic graph (DAG) models. Building on recent developments in exact estimation of DAGs using integer linear programming (ILP), we present an ILP approach for joint estimation over multiple DAGs. Unlike previous work, we do not require that the vertices in each DAG share a common ordering. Furthermore, we allow for (potentially unknown) dependency structure between the DAGs. Results are presented on both simulated data and fMRI data obtained from multiple subjects.",

keywords = "Hierarchical model, Bayesian network, Multiregression dynamical model, Integer linear programming, Joint estimation",

author = "Oates, \{Chris J.\} and Smith, \{Jim Q.\} and Sach Mukherjee and James Cussens",

note = "Funding Information: CJO was supported by the Centre for Research in Statistical Methodology (CRiSM) EPSRC EP /D002060/1. JC was supported by the Medical Research Council (Project Grant G1002312). SM was supported by the UK Medical Research Council and is a recipient of a Royal Society Wolfson Research Merit Award. Publisher Copyright: {\textcopyright} Springer Science+Business Media New York 2015.",

year = "2016",

month = jul,

day = "1",

doi = "10.1007/s11222-015-9570-9",

language = "English",

volume = "26",

pages = "797–811",

journal = "Statistics and Computing",

issn = "0960-3174",

publisher = "Springer",

}

TY - JOUR

T1 - Exact estimation of multiple directed acyclic graphs

AU - Oates, Chris J.

AU - Smith, Jim Q.

AU - Mukherjee, Sach

AU - Cussens, James

N1 - Funding Information: CJO was supported by the Centre for Research in Statistical Methodology (CRiSM) EPSRC EP /D002060/1. JC was supported by the Medical Research Council (Project Grant G1002312). SM was supported by the UK Medical Research Council and is a recipient of a Royal Society Wolfson Research Merit Award. Publisher Copyright: © Springer Science+Business Media New York 2015.

PY - 2016/7/1

Y1 - 2016/7/1

N2 - This paper considers structure learning for multiple related directed acyclic graph (DAG) models. Building on recent developments in exact estimation of DAGs using integer linear programming (ILP), we present an ILP approach for joint estimation over multiple DAGs. Unlike previous work, we do not require that the vertices in each DAG share a common ordering. Furthermore, we allow for (potentially unknown) dependency structure between the DAGs. Results are presented on both simulated data and fMRI data obtained from multiple subjects.

AB - This paper considers structure learning for multiple related directed acyclic graph (DAG) models. Building on recent developments in exact estimation of DAGs using integer linear programming (ILP), we present an ILP approach for joint estimation over multiple DAGs. Unlike previous work, we do not require that the vertices in each DAG share a common ordering. Furthermore, we allow for (potentially unknown) dependency structure between the DAGs. Results are presented on both simulated data and fMRI data obtained from multiple subjects.

KW - Hierarchical model

KW - Bayesian network

KW - Multiregression dynamical model

KW - Integer linear programming

KW - Joint estimation

U2 - 10.1007/s11222-015-9570-9

DO - 10.1007/s11222-015-9570-9

M3 - Article (Academic Journal)

SN - 0960-3174

VL - 26

SP - 797

EP - 811

JO - Statistics and Computing

JF - Statistics and Computing

ER -

Exact estimation of multiple directed acyclic graphs

Abstract

Bibliographical note

Keywords

Access to Document

Handle.net

Fingerprint

Cite this