Ashlynn Crisp Stat 501 Presentation

Title: Scaling the Nearest Neighbor Gaussian Process

Abstract:
Gaussian processes are ubiquitous as the primary tool for modeling spatial
data. However, the Gaussian process is limited by its O(n 3 ) cost, making direct
parameter fitting algorithms infeasible for the scale of modern data collection
initiatives. The Nearest Neighbor Gaussian Process (NNGP) was proposed by
Datta et al. (2016) as a scalable approximation to dense Gaussian processes
which has been successful for n ∼ 10 6 observations. This project introduces
the clustered Nearest Neighbor Gaussian Process (cNNGP) which reduces the
computational and storage cost of the NNGP. The accuracy of parameter estimation
and reduction in computational and memory storage requirements are
demonstrated with simulated datasets.