Fully-funded PhD studentship at University College London

Fully funded PhD studentship in Statistical Regularisation at
University College London, UK
---
Duration of studentship: 3 years
Stipend: £15,863 per annum
Studentship start date: 28th September 2015 or shortly thereafter
Application closing date: Applications will be considered on a rolling
basis until the studentship is filled. Apply as soon as possible to
avoid disappointment!
---
Applications are invited for a fully funded PhD studentship in
"Statistical regularisation" at UCL. The studentship will commence 28th
September 2015 or shortly thereafter, will be based in UCL's Department
of Statistical Science, and will involve an extended visit (approx one
year) to the Japanese Advanced Institute of Science and Technology
(JAIST). The award is tenable for 36 months and covers tuition fees plus
a stipend of £15,863 per annum (based on the standard UK Research
Council rate with London weighting).
This studentship may only be awarded to applicants liable to pay tuition
fees at the UK/EU rate (i.e. it cannot be used to part-cover overseas
tuition fees).
---
*Studentship Description*
The project will address the current need to progress new sparse,
adaptive statistical models and approaches that have the capability to
capture both the rich statistical, and structural, interdependencies
present in high-dimensional image data sets. The work will draw on a
combination of recent ideas that attempt to (i) accommodate both
correlatory and relational interactions of heterogeneous data over, and
between, multiple scales and (ii) extract, learn, and predict sparse
representations of the data in an adaptive and robust manner.
The techniques of interest cross several allied research areas.
Candidates with an interest in one or more of the following are
particularly encouraged to apply: regression and various manifestations
of the Lasso, compressive sensing, dictionary learning and sparse
coding, Gaussian processes, Markov random fields, and/or stochastic
geometry.
Statistical techniques such as these continue to enjoy increasing
attention in many modern, so-termed, data science problems. A key driver
for this interest is the advent of recent innovations in smart
technology domains such as sensors, mobile computing, and robotics
where, for example, 'smart objects', unmanned vehicles, and sensor
networks are set to effect significant and long-lasting impact on a
multitude of sectors. Owing to the abundance of data captured from
these persistent, always-on, next-generation systems there is an urgent
and growing demand for statistically well-principled data analysis and
signal/image processing.
It is against this general backdrop that the candidate will be afforded
bountiful scope and motivation to develop interesting, and hitherto
unexplored, statistical models and methodology. There will,
furthermore, also exist ample opportunities to work alongside, and
interact with, the immediate research group--- a focused team of
other PhD students and post-docs, from myriad backgrounds, with various
projects and interests in this space, at UCL, JAIST, and collaborators
at Cambridge University, Intel, and beyond.
*Person Specification*
The requirement for admission to the MPhil/PhD in Statistical Science is
a 1st class or high upper 2nd class BSc degree, or an MSc with merit or
distinction in Mathematics, Statistics, Computer Science, Engineering,
or a related quantitative discipline. Overseas qualifications of an
equivalent standard are also acceptable.
Informal enquiries to Dr James Nelson
http://www.ucl.ac.uk/statistics/people/jamesnelson
are welcomed
*How to apply*
Candidates should apply for the Research Degree: Statistical Science
(RRDSTASING01) in the usual way by completing the online form at:
http://www.ucl.ac.uk/prospective-students/graduate...
and, to help notify us of potential candidates early, send a covering
letter/email directly to Dr. James Nelson