4 papers
Partial correlation networks of Gaussian processes
Michele Peruzzi
In Gaussian graphical models, conditional independence and partial correlations are natural inferential targets for understanding direct relationships in multivariate data. No comp…
Gridding and Parameter Expansion for Scalable Latent Gaussian Models of Spatial Multivariate Data
Michele Peruzzi, Sudipto Banerjee, David B. Dunson +1
Scalable spatial GPs for massive datasets can be built via sparse Directed Acyclic Graphs (DAGs) where a small number of directed edges is sufficient to flexibly characterize spati…
Bag of DAGs: Inferring Directional Dependence in Spatiotemporal Processes
Bora Jin, Michele Peruzzi, David Dunson
We propose a class of nonstationary processes to characterize space- and time-varying directional associations in point-referenced data. We are motivated by spatiotemporal modeling…
Radial Neighbors for Provably Accurate Scalable Approximations of Gaussian Processes
Yichen Zhu, Michele Peruzzi, Cheng Li +1
In geostatistical problems with massive sample size, Gaussian processes can be approximated using sparse directed acyclic graphs to achieve scalable computational complexity…