Lindon Roberts

Lindon Roberts is a Lecturer in the School of Mathematics and Statistics at the University of Sydney. He holds a DPhil (Doctor of Philosophy) from the University of Oxford and previously served as an MSI Fellow at the Australian National University. His research focuses on numerical optimization, including nonconvex, derivative-free, and stochastic optimization, with applications in machine learning. He currently teaches courses such as MATH2070 (Optimization and Financial Mathematics) and FMAT3888 (Projects in Financial Mathematics).

Education & Professional Background:

• PhD (DPhil) in Mathematics, University of Oxford
• MSI Fellow, Australian National University

Research Interests:

• Numerical optimization techniques
• Derivative-free and stochastic optimization methods
• Algorithm design for machine learning applications
• Nonconvex optimization challenges

His work bridges theoretical optimization and practical implementation, particularly in imaging and data-driven fields.

Funding & Grants:

• 2024: 'Robust Derivative-Free Algorithms for Complex Optimisation Problems' (Australian Research Council DECRA)
• 2022: 'Theory and Algorithms for Numerical Optimisation' (University of Sydney Faculty Startup)

Key Research Trends in Publications: Recent articles emphasize optimization algorithms for imaging (e.g., X-ray and neutron beam techniques) and bilevel learning frameworks. His work on inexact hypergradients and scalable subspace methods highlights advancements in handling complex optimization landscapes.