Gavin Brown

Professor Gavin Brown is a faculty member in the Department of Computer Science, focusing on theoretical and methodological foundations of Machine Learning. His work bridges statistics, information theory, and information geometry to develop robust ML methods for reproducibility and hypothesis testing in non-standard scenarios.

His research has been applied to predictive policing, clinical trials, and energy-efficient ML algorithms for plastic electronics. Key publications include A Unified Theory of Diversity in Ensemble Learning (JMLR, 2023) and On the Stability of Feature Selection in the Presence of Feature Correlations (ECML, 2019), supported by EPSRC funding.

Recent work (2024) investigates the distinction between bias-variance and approximation-estimation error, alongside hardware-efficient ML solutions for FPGAs and flexible electronics. His book How to Get Your PhD (OUP, 2021) offers practical and emotional guidance for doctoral students, co-authored with 12 experts on career planning, diversity in science, and risk management in research.

• Developed theories for ensemble diversity (2020-2023)
• Created stability metrics for feature selection (2016-2022)
• Explored ML applications in healthcare and public safety

Current activities include a research sabbatical (2021-2022) working on novel ML frameworks. He leads a research group at the Kilburn Building (Office G11) and contributes to pedagogy discussions, particularly around PhD training and conceptual understanding in deep learning.