Fred Roosta

Next generation Newton-type methods with minimum residual solver

A fully funded PhD position in the School of Mathematics and Physics at The University of Queensland, focused on the development and analysis of next-generation Newton-type optimisation methods. The project addresses fundamental questions in large-scale optimisation and numerical linear algebra, with strong connections to modern machine learning and scientific computing.

Applicants should have a strong background in applied mathematics, optimisation, linear algebra, or closely related areas, with experience in programming (e.g. Python).

The position is supported by a competitive scholarship covering tuition fees and a living stipend.

Further details and application instructions are available on the project webpage:https://study.uq.edu.au/study-options/phd-mphil-professional-doctorate/projects/next-generation-newton-type-methods-minimum-residual-solver

Non-convex Optimization for Machine Learning

Design, analysis, and implementation of novel optimization algorithms for optimization of modern non-convex machine learning problems.

Interpretable AI - Theory and Practice

This project will extend and innovate, both theoretically and practically, interpretable methods in AI that are transparent and explainable to improve trust and usability. It will also explore novel approaches for uncertainty quantification and understanding causality.

Exploring Predictivity--Parsimony Trade-off In Scientific Machine Learning

This project will investigate, both theoretically and empirically, novel statistical techniques to explore the trade-offs between high-generalization performance and low-model complexity for scientific machine learning.