Connectionists: PhD Studentship in Quantum Machine Learning

[Mark Herbster]

PhD Studentship in Quantum Machine Learning
University College London 
Department of Computer Science
 

A fully funded PhD studentship is available for UK students.  It will suit students with a strong background in mathematics, physics, or theoretical computer science. 

The aim of this PhD position is to design and analyse efficient algorithms for quantum machine learning.  We are interested in both algorithms that may be implemented with currently envisioned quantum computing devices as well as the efficient implementation on classical computers of quantum-inspired algorithms.

A common framework for machine learning is regularised risk minimisation. The idea is that given a dataset we should select a hypothesis which trades off “fit to the data” and “complexity” of the hypothesis. Standard examples of regularisers for linear prediction include the 2-norm, 1-norm and maximum entropy.  A number of machine learning problems may be framed as “matrix learning” - these include for example collaborative filtering, metric learning, and multi-task learning. A popular approach to these problems is the use of spectral matrix regularisers, where the regulariser may be expressed as a function of singular values of the matrix predictor.  The project goal is to develop quantum approaches to spectral regularisation.  Practically, we will be concerned with the application of matrix learning to scheduling and network transport problems. 

This project will be jointly supervised by Mark Herbster, Massimiliano Pontil, and Simone Severini.  Please see https://www.prism.ucl.ac.uk/#!/?project=140 for further details.


Regards,
Mark Herbster