James Cussens
[Research]
[PhD supervision]
[Projects]
[Software]
[Teaching]
[Professional
Activities]
[Administration]
[Personal history]
[Contact information]
[Dept home page]
Research
Google scholar profile
GOBNILP software for exact Bayesian network learning
Topics for prospective PhD students
Recent papers

Nuala Sheehan, Mark Bartlett and James Cussens.
Improved Maximum Likelihood Reconstruction of
Complex Multigenerational Pedigrees. Theoretical
Population Biology. In Press.
 Chris J. Oates, Jim Q. Smith, Sach Mukherjee and James
Cussens. Exact Estimation of
Multiple Directed Acyclic Graphs. Arkiv 1404.1238,
April 2014.

James Cussens. Leibniz on Probability and Statistics. In
Maria Rosa Antognazza, editor, The
Oxford Handbook of Leibniz. Oxford University
Press. March 2014.

James Cussens. Probability, Uncertainty and Artificial Intelligence. Metascience, (In press).

Lilia Costa, Jim Smith, Thomas Nichols and James
Cussens. Searching Multiregression Dynamic Models of RestingState fMRI Networks using Integer Programming. Working paper
1320, Centre for Research in Statistical Methodology
(CRiSM), University of Warwick, 2013.

James Cussens. Integer Programming for Bayesian
Network Structure Learning. Quality
Technology and Quantitative Management,
11(1):99110,
March 2014.

Mark Barlett and James Cussens.
Advances in Bayesian Network Learning using Integer
Programming.
Proceedings of the 29th Conference on Uncertainty in
Artificial Intelligence (UAI 2013). 182191, 2013.

Joanne Powell, Matthew J. Collins, James Cussens,
Norman MacLeod and Kirsty E.H. Penkman.
Results
from an amino acid racemization interlaboratory proficiency
study; design and performance
evaluation. Quaternary Geochronology, 16:183197, 2013.
 James Cussens, Mark Bartlett, Elinor M. Jones and Nuala
A. Sheehan.
Maximum Likelihood Pedigree Reconstruction using
Integer Linear Programming. Genetic Epidemiology, 37(1):6983, Janary 2013.
Recent talks

Bayesian Network Model Selection using Integer
Programming, Dept of Statistics, University of Leeds, 4
October 2013.

Integer Programming for Bayesian Network Structure Learning, Czech Academy of Sciences, Prague, 2 September 2013.

Advances in Bayesian Network Learning using Integer
Programming , UAI 13, Bellevue, USA, 12 July 2013.

Integer Programming for Bayesian Network Structure Learning ,
Helsinki Institute for Information Technology, 4 April 2013.

Integrating Constraint Programming and Integer Programming
with SCIP,
KU Leuven, 25 February 2013.
Current PhD students

Garo Panikian  Statistical
inference of dynamical systems with application to modelling
fish populations

Eman Aljohani  Informative priors for learning graphical
models
Former students

Waleed Alsanie  Learning
PRISM programs

Joanne Powell  PrediCtoR: Predicting the Recovery of
Ancient DNA and Ancient Proteins (with Matthew
Collins, Archaeology)

Adel Aloraini  Extending the graphical represetation of KEGG pathways for a better understanding of prostate cancer using machine learning

Barnaby Fisher 
Inductive Logic Programming and Mercury (MSc by Research)

Heather
Maclaren

Inductive Logic Programming for Software Agents:
Algorithms and Implementations
My main research interests are in machine learning,
probabilistic graphical models and discrete optimisation using
integer programming. I also work on statistical relational
learning and, occasionally, philosophy of probability. Here are some
possible topics for a PhD. Let me know if you're interested!

Model selection for graphical models using integer
programming. I have recently been working on this
problem. However, to date, we have restricted attention to
learning directed graphical models ('Bayesian networks')
from complete discrete data. Extending this approach to
other graphical model learning problems is an exciting
research area. Problems include: learning Gaussian graphical
models (decomposable or unrestricted), chain event graphs,
nongraphical loglinear models (probably restricted to
hierarchical ones), etc, etc.

From optimisation to integration. In Bayesian
statistics finding the most probable model is useful and I
have applied integer programming to solve this optimisation
problem (for directed graphical models with complete
discrete data). However a full Bayesian approach requires
consideration of the entire posterior distribution over
models. Typically one wants to compute some marginal
posterior quantity (e.g. the posterior probability that some
edge exists in a graphical model). This requires computing
weighted sums (discrete integration) over a very large set (eg the set of all
acyclic
digraphs). Recent
work by Ermon and colleagues has shown that one can get
good approximations to this sum by repeatedly solving optimisation
problems with random constraints. This area
merits further research. In particular it would be useful to
compare it to MCMC approaches to the same problem.

Mixed integer programming for product space
approaches. Integer programming has been used for
Bayesian model selection when it has been possible to
analytically 'integrate away' model parameters. This is, of
course, a big restriction. It would be useful to look into
applying mixed integer programming (where both discrete and
continuous variables are used) to sampling from a 'product
space' encoding both models (discrete) and parameters
(continuous). An extension to the 'random constraint'
approach mentioned above should allow such sampling to be
reduced to repeated optimisations.
To undertake research in these areas it is necessary to have a
strong mathematical background. Unfortunately, I have no
specific funding available to support graduate students. Our
department does award funded
research studentships on a competitive basis.
Software
 GOBNILP software for exact Bayesian network learning
 gPy is a collection of
Python modules for manipulating discrete hierarchical models
(including Bayesian nets). It is used to support the
teaching of Algorithms for Graphical
Models.
 The
MCMCMS (Markov chain Monte Carlo over Model Structures)
system
uses Stochastic Logic Programs (SLPs) to define priors for
Bayesian inference. The code was written by
Nicos Angelopoulos.

Pepl
is an implementation of the FailureAdjusted Maximisation
(FAM) algorithm.This is an instance of the EM algorithm which
produces maximum likelihood estimates for the parameters of
SLPs. The code was written by Nicos Angelopoulos.

Aaron Bate, a final year student in this department, has
produced software for animating the construction of Prolog
proof trees (the software draws a graphical representation
of the proof tree). It uses Sicstus Prolog and Tcl/Tk. You can download the software as a gzipped
tar file. I have included a simple Prolog SLP
interpreter which allows you to sample from a distribution
over proof trees and where each proof tree determines an
acyclic digraph (the structural element of a Bayesian
net). See the file slp_readme in the distribution
for an explanation.
Projects
Teaching
Currently, at York:
Professional Activities
Programme chair
Editorial duties
Member
Invited speaker
Area chair/Senior PC
Coorganiser
PC member

AAAI15

ICML
2014,
UAI 2014,
ILP
2014,
ECML/PKDD 2014,
AAAI14,
KR 2014,
ECAI'14,
CoCoMiLe
2014,
BUDA 2014,

ICML 2013,
UAI 2013,
ILP 2013,
ECML/PKDD 2013,
EMNLP 2013,
NAACLHLT 2013,
LML workshop at ECML/PKDD 2013

ICML 2012,
UAI 2012,
ILP 2012,
ECML/PKDD 2012,
AAAI12,
KR 2012
StaRAI12,
CoCoMile 2012,
ACL 2012,
Cognitive 2012,

ICML 2011,
UAI 2011,
ILP 2011,
ECML/PKDD 2011,

ILP 2010,
AAAI10,
ECAI2010,
ECML/PKDD 2010,
SBIA 2010

ICML 09,
ILP09,
SRL09,
Terminologie et intelligence artificielle (TIA  2009),
IJCAI09,
AISTATS
09, CoNLL 09, NAACLHLT 09,
EACL
Cognitive 2009, NAACL2009 Workshop on Unsupervised and Minimally Supervised Learning of Lexical Semantics

ICML 08,
ILP 08,
ECAI 08,
SBIA 08,
CoNLL 08,
 ICML
07,
UAI07, ILP07, ACL2007 Workshop on Cognitive Aspects of Computational Language Acquisition, TIA'07

UAI06,
ILP06,
AAAI06,
SRL06,
CoNLL06

ICML05,
UAI05,
ILP05,
ECML/PKDD05,
LLLL,
CoNLL05,
TIA05

ICML04,
UAI04,
ECML04,
CIFT04,
SRL04,
CoNLL04,
Psychocomputational models ...

ICML03,
UAI03,
ILP03,
CoNLL03,
Acquisition, apprentissage et ...,
SRL2003,
ECML03

ICML02,
UAI02,
ILP02,
CIFT02,
CoNLL02

ILP01,
ECML01
,
CoNLL01,
LLL01

ILP00,
CoNLL00,
LLL00

ILP99
,
LLL99
 ILP98
Reviewer
Miscellaneous
Administration
Personal history
Contact information
Address

Dept of Computer Science and
York Centre for Complex Systems Analysis,
Room 326, The Hub, Deramore Lane, University of York, York, YO10 5GE, UK 
Direct phone

+44 1904 325371 
Fax

+44 1904 500159 
firstname.lastname AT cs DOT york DOT ac DOT uk
