معرفی
Dr. Matt Sutton is a Lecturer in Statistical Inference for Complex Models at the School of Mathematical Sciences. He earned his PhD in 2019, focusing on developing statistical methods for high-dimensional data in clinical health and biological contexts. Previously, he worked as a postdoc at Lancaster University under the Bayes4Health grant. His research emphasizes Monte Carlo methods, Bayesian methodology, and high-dimensional statistics, with a current focus on continuous-time Monte Carlo techniques to accelerate Bayesian inference. Sutton actively contributes to the Models and Algorithms research program at the Centre for Data Science.
His research interests include computational statistics, specifically advancements in PDMP samplers, control variates, and scalable Bayesian methods. Notable work spans applications in genomics, geophysics, and healthcare data analysis. Sutton’s methodologies aim to enhance computational efficiency in complex statistical inference tasks.
His articles reflect a trend toward optimizing sampling algorithms and addressing challenges in high-dimensional Bayesian problems. Key areas include PDMP-based sampling, debiasing techniques, and federated learning applications. Sutton has not yet reported formal scientific awards or listed advisees in the provided text. His involvement in collaborative initiatives like the Centre for Data Science underscores his commitment to interdisciplinary research.
