A fully funded PhD scholarship working at the interface between statistics
and machine learning is available at the University of Sheffield within the
School of Mathematics and Statistics. This is supported by Microsoft
Research and EPSRC through Microsoft’s PhD Scholarship Programme. It will
provide four years of funding with an enhanced stipend of £18,777 per year,
and comes with a generous training budget for conference travel and
The student will be supervised by Professor Richard Wilkinson and Professor
Jeremy Oakley, and is in collaboration with Dr Ted Meeds from Microsoft
The position is open to applications from UK or EU students who hold, or
expect to soon obtain, distinction-level MSc or First-class degrees in
maths, computer science or physics (or equivalent).
The project will develop new inferential approaches for misspecified
Mechanistic or simulation-based models are used in scientific research to
understand complex natural phenomena. A mechanistic model can take the form
of ordinary/partial/stochastic differential equations (O/P/SDEs) and can be
rigid in form but have the benefit to the scientist of having interpretable
and testable parameter settings. In part due to the inflexibility of the
model forms, misspecification of the model can lead to computationally
expensive inference procedures, and more importantly, misleading
conclusions, whereby the parameter estimates are confidently incorrect.
There is increasing evidence that the inference framework called
approximate Bayesian computation (ABC) is more robust to model
misspecification than other inferential approaches. We propose to study the
mathematical and statistical properties of this robustness, and explore
improvements of current approaches for dealing with model misspecification.
The research will be pragmatic, embedding the theory with practical
examples (where domain knowledge is understood, and hence misspecification
can be detected), including using semi-mechanistic models that are used in
the public health domain.
The studentship is an industrial CASE award from Microsoft Research and
Microsoft’s PhD Scholarship Programme. As such, the student will have the
opportunity to interact with the machine learning research group at
Microsoft Research Cambridge (MSR), and will be expected to spend time in
Cambridge visiting Dr Ted Meeds at MSR.
Further details are available by contacting Professor Richard Wilkinson -
email: [log in to unmask]; web: http://r-wilkinson.staff.shef.
ac.uk; phone 0114 22 23728.
Applications should be submitted online at
stating that you wish to apply for the Mechanistic Model Misspecification
There is no formal closing date, and applications will be considered on
merit as they arrive.
You may leave the list at any time by sending the command
to [log in to unmask], leaving the subject line blank.