Fully Funded Studentship – StatML CDT

Due to funding constraints to be eligible for this studentship you need to be classified as a home student. Please see eligibility criteria here:  Eligibility for studentship funding – UKRI.

Deadline for Applications:  17 August 2022 by 17.00

Academic Supervisors: Ruth Misener and Mark van der Wilk (Imperial).

Contact r.misener@imperial.ac.uk                         

Project Title:  Data-driven optimization of hierarchical engineering systems

This project addresses the data-driven optimization of hierarchical engineering systems. We will study Bayesian optimization when decision depend on one another. To understand the challenge, consider a (fictional) optimization example with a chemical reaction that can run in reactor A or reactor B. Reactor A is a batch reactor where temperature and stirrer speed can be controlled. Reactor B is a tubular reactor with a defined temperature but no stirrer because the reactants just flow through. For Reactor B, it would not be relevant to just set the stirrer speed to 0 because the entire geometry of the reactor is different. The black-box optimizer would have to choose between reactors A and B and then set the parameters that are active for that setup.

We have presented the challenge in light of an engineering application, but there are many other applications including hyper parameter optimization in machine learning.

In addition to doing research, the student will have the opportunity to contribute to our team’s open-source software packages. The current project is part of a bigger research collaboration between Imperial and BASF.

The successful candidate will be part of the Modern Statistics and Statistical Machine Learning Centre for Doctoral Training and will be required to take courses and attend events as part of the cohort.  

To apply please send an up-to-date CV to statml.io.admissions@imperial@ac.uk with the subject “Application – Data-driven optimization of hierarchical engineering systems”.

Close Menu