Wednesday, January 13, 2021 - 3:30pm to 4:30pm
- Zoom Meeting
Title: Scalable Gaussian-Process Approximations for Big Data
Gaussian processes (GPs) are popular, flexible, and interpretable probabilistic models for functions in geospatial analysis, computer-model emulation, and machine learning. However, direct application of GPs involves dense covariance matrices and is computationally infeasible for large datasets. We consider a framework for fast GP inference based on the so-called Vecchia approximation, which implies a sparse Cholesky factor of the inverse covariance matrix. The approximation can be written in closed form and computed in parallel, and it includes many popular existing approximations as special cases. We discuss applications of the framework to noisy and non-Gaussian data and to the analysis of computer experiments. Further extensions allow nonparametric inference on the covariance matrix, with applications in climate-model emulation and data assimilation.
Matthias Katzfuss is an Associate Professor in the Department of Statistics at Texas A&M University. His research interests include spatial and spatio-temporal statistics, Gaussian processes, computational statistics for massive datasets, and data assimilation, with applications to environmental problems and satellite remote-sensing data. His research has been funded by NSF, NASA, NOAA, USDA, and the Jet Propulsion Laboratory. Matthias is the recipient of an NSF Career Award, a Fulbright Scholarship, and an Early Investigator Award by the ASA Section on Statistics and the Environment.
December 30, 2020 - 2:16pm