Matthew Thorpe

Matthew Thorpe is an Associate Professor in the Department of Statistics at the University of Warwick and a member of the European Laboratory for Learning and Intelligent Systems (ELLIS). His research focuses on applying methods from applied analysis—including partial differential equations (PDEs), calculus of variations, and optimal transport—to machine learning and data science challenges. He has organized workshops such as the 'Machine Learning in Infinite Dimensions' at ETH Zurich and the 'LMS-Bath Symposium on Inverse Problems and Artificial Intelligence in Medicine.' Thorpe currently seeks PhD students for his research projects. His work bridges theoretical mathematics with practical applications in data-driven fields.

Thorpe's research interests include manifold learning in Wasserstein space, PDE-based approaches to data science, and convergence analysis of graph-based learning algorithms. He has contributed to understanding the impact of imputation quality on machine learning models and developed novel transportation distances for pattern recognition. His interdisciplinary approach integrates mathematical rigor with advancements in artificial intelligence.

He has co-organized the One World Seminar Series on the Mathematics of Machine Learning and remains active in promoting collaborative research initiatives. Despite no explicitly listed awards, his prolific publication record reflects sustained academic impact. Thorpe’s advising focuses on training students in the intersection of applied mathematics and modern data science techniques.