Neural Methods for Amortized Inference with Models for Spatial Extremes
Neural Bayes estimators are neural networks that approximate Bayes estimators. Once trained, these estimators are not only statistically efficient, but also extremely fast to evaluate and amenable to rapid uncertainty quantification. Neural Bayes estimators thus have compelling advantages when used with spatial models that have a computationally intractable likelihood function, as often the case when modeling spatial extremes. In this talk, I will showcase the power of neural Bayes estimators for spatial extremes in a range of climate-related and geo-environmental data applications.
Overview
Presenters
Brief Biography
Raphaël Huser is an Associate Professor of Statistics and the principal investigator of the Extreme Statistics (XSTAT) research group. He is also affiliated with the Applied Mathematics and Computational Science (AMCS) Program.
Professor Huser received his Ph.D. in Statistics in 2013 from the Swiss Federal Institute of Technology, Switzerland, under the supervision of Professor Anthony C. Davison. He also holds a B.S. in Mathematics and an M.S. in Applied Mathematics from École polytechnique fédérale de Lausanne (EPFL), Switzerland.
After completing his Ph.D., Huser joined KAUST as a postdoctoral research fellow in January 2014. He was appointed Assistant Professor in March 2015 and promoted to Associate Professor of Statistics in 2022.
