Matthew Sainsbury-Dale
Matthew Sainsbury-Dale's research focuses on statistical deep learning, simulation-based inference, spatial and spatio-temporal statistics, and the development of efficient statistical software.
Biography
Matthew Sainsbury-Dale is a Research Scientist in the Statistics Program at King Abdullah University of Science and Technology (KAUST), where he works in the Extreme Statistics (XSTAT) research group led by Associate Professor Raphaël Huser. His research sits at the interface of statistics and machine learning, with a focus on spatial and spatio-temporal statistics and the use of deep learning for fast, simulation-based inference in complex statistical models.
Matthew places a strong emphasis on open source software that makes new statistical methods readily available in practice. He is the lead developer of the package NeuralEstimators, available in Julia and R for efficient simulation-based inference using neural networks. He is also a co-developer of the R package FRK for modeling big spatial and spatio-temporal data.
Matthew obtained his Bachelor of Mathematics (Honours First Class) in 2019 and his Ph.D. in Statistics in 2024 from the University of Wollongong (UOW), Australia, under the supervision of Associate Professor Andrew Zammit-Mangion and Distinguished Professor Noel Cressie. His thesis, "Efficient Inference for Spatial and Spatio-Temporal Statistical Models Using Basis-Function and Deep-Learning Methods", received the Examiners Commendation for Outstanding Thesis and the Faculty of Engineering and Information Sciences Postgraduate Thesis Award. The Statistical Society of Australia recognized his doctoral work with three awards: the JB Douglas Award for Excellence in Postgraduate Research, the Tjanpi Award for Best Student Paper in Environmental Statistics, and the Venables Award for New Developers of Open Source Software for Data Analytics.
Expertise and Interests
Matthew Sainsbury-Dale's research focuses on statistical deep learning, simulation-based inference, spatial and spatio-temporal statistics, and the development of efficient statistical software.
Awards and Distinctions
- Venables Award for New Developers of Open Source Software for Data Analytics, Statistical Society of Australia (SSA), 2023
- JB Douglas Award for Excellence in Postgraduate Research, Statistical Society of Australia (SSA), 2023
- Examiners Commendation for Outstanding Thesis, University of Wollongong (UOW), 2024
- Faculty of Engineering and Information Sciences Postgraduate Thesis Award, University of Wollongong, 2024
- Tjanpi Award for Best Student Paper in Environmental Statistics, Statistical Society of Australia (SSA), 2023
- American Statistical Association (ASA) Section on Bayesian Statistical Science (SBSS) Student Paper Competition, American Statistical Association (ASA), 2024
Education
- Doctor of Philosophy (Ph.D.)
- Statistics, University of Wollongong (UOW), Australia, 2024
- Bachelor of Science (B.S.)
- Mathematics, University of Wollongong (UOW), Australia, 2019