Skip to:

Biostatistics Fall 2019 Seminar | Gaussian-Process Approximations for Big Data

Biostatistics Fall 2019 Seminar | Gaussian-Process Approximations for Big Data

Date 
Wednesday, November 13, 2019 - 3:30pm to 4:30pm
Location 
CHS 33-105A Los Angeles , CA
California US
Featuring 
Matthias Katzfuss
Event Contact 

wkwong@ucla.edu
310-206-9622

Matthias Katzfuss
Associate Professor
Department of Statistics at Texas A&M University

Gaussian processes (GPs) are popular, flexible and interpretable probabilistic models for functions. GPs are well suited for big data in areas such as machine learning, regression, and geospatial analysis. However, direct application of GPs is computationally infeasible for large datasets. We consider a framework for fast GP inference based on the so-called Vecchia approximation. Our framework contains many popular existing GP approximations as special cases. Representing the models by directed acyclic graphs, we determine the sparsity of the matrices necessary for inference, which leads to new insights regarding the computational properties. Based on these results, we propose novel Vecchia approaches for noisy, non-Gaussian and massive data. We provide theoretical results, conduct numerical comparisons and apply the methods to satellite data.

Refreshments served at 3:00pm in CHS 51-254
Hosted by Department of Biostatistics at UCLA