PhD Stipend @ The University of Melbourne

Research topic: Nonmonotone Algorithms in Operator Splitting, Optimisation and Data Science

Brief outline: You will work with Dr Matthew Tam (University of Melbourne) as part of the ARC 2020 DECRA Project “Nonmonotone Algorithms in Operator Splitting, Optimisation and Data Science”. This project aims to develop the mathematical foundations for the analysis and development of optimisation algorithms used in data science.

Stipend amount: Approximately $31400 per annum.

Detailed description: This project aims to develop the mathematical foundations for the analysis and development of optimisation algorithms used in data science. Despite their now ubiquitous use, machine learning software packages routinely rely on a number of algorithms from mathematical optimisation which are not properly understood. By moving beyond the traditional realms of Fejér monotone algorithms, this project expects to develop the mathematical theory required to rigorously justify the use of such algorithms and thereby ensure the integrity of the decision tools they produce. This mathematical framework is also expected to produce new algorithms for optimisation

Eligibility criteria: Applicants must:

Application procedure: Interested applicants should send Dr Matthew Tam (firstname.lastname@unimelb.edu.au) a cover letter (with a statement of research interests and suitability for the position) and CV.