Imperial College London Featured PhD Programmes
Birkbeck, University of London Featured PhD Programmes
Engineering and Physical Sciences Research Council Featured PhD Programmes
University of Warwick Featured PhD Programmes
University of Reading Featured PhD Programmes

High dimensional learning with theoretical guarantees

  • Full or part time
    Prof A Kaban
  • Application Deadline
    Friday, February 28, 2020
  • Funded PhD Project (European/UK Students Only)
    Funded PhD Project (European/UK Students Only)

Project Description

A PhD position is available in the area of machine learning, to develop novel algorithms with theoretical guarantees on performance, and apply such algorithms to early diagnosis in healthcare.

In many application areas in machine learning, data sets become increasingly high dimensional and noisy, while sample sizes remain moderate. In such conditions learning to make predictions and generalisation from the data is provably impossible in general - yet, machine learning algorithms are expected and often do perform in applications. When and how can this be rigorously guaranteed?

The successful candidate will join our research on FORGING: Fortuitous Geometries and Compressive Learning (https://gtr.ukri.org/projects?ref=EP%2FP004245%2F1), where we develop ways to formalise the intuition that realistic data sources and learning problems often exhibit certain benign properties or hidden structure that facilitate learning. We should take advantage of such structures both to strengthen theoretical guarantees, and to devise better learning algorithms.

We seek an ambitious PhD candidate with excellent problem solving ability, and excellent programming skills. There are ample opportunities to develop and pursue interdisciplinary collaborations.

Funding Notes

The position offered is for three and a half years full-time study. The value of the award covers stipend: £15,009 pa and tuition fee: £4,327 pa. Awards are usually incremented on 1 October each year.

Eligibility: 2:1 Honours undergraduate degree and/or postgraduate degree with Distinction (or an international equivalent) in a numerate subject, such as Mathematics, Statistics, Computer Science or Physics. Excellent problem solving skills and programming skills are required.

If your first language is not English and you have not studied in an English-speaking country, you will have to provide an English language qualification.

References

H.W.J. Reeve, A. Kaban. Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label Noise. International Conference on Machine Learning (ICML 2019), Proceedings of Machine Learning Research, Vol 97, pp. 5401-5409.

H. Reeve, A. Kaban. Robust randomised optimisation with k nearest neighbours, Analysis and Applications, Special Issue on Mathematics of Big Data: Deep Learning, Approximation and Optimization, 2019,

A. Kaban, Y. Thummanusarn. Tighter guarantees for the compressive multi-layer perceptron. Proceedings of the 7th International Conference on the Theory and Practice of Natural Computing (TPNC 2018), pp. 388-400.

A. Kaban, J. Bootkrajang, R.J. Durrant. Towards Large Scale Continuous EDA: A Random Matrix Theory Perspective. Evolutionary Computation 24(2): 255-291, 2016, MIT Press.

R.J. Durrant, A. Kaban. Random projections as regularizers: Learning a linear discriminant from fewer observations than dimensions. Machine Learning 99(2), pp. 257-286, 2015.

See more at: http://www.cs.bham.ac.uk/~axk/papers_by_yr.htm

How good is research at University of Birmingham in Computer Science and Informatics?

FTE Category A staff submitted: 40.60

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully





FindAPhD. Copyright 2005-2020
All rights reserved.