A hierarchical sparse Gaussian process for in situ inference in expensive physics simulations

Rumsey, Kellin N.; Grosskopf, M.J.; Lawrence, Earl; Biswas, Ayan; Urban, Nathan M.

doi:10.1117/12.2633427

Cited by 2 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regardless, leapGP has a relatively small overhead and will at worst be computational comparable with laGP. We begin with the analysis of a simple bivariate function, studied by Rumsey et al (2022) in the context of large-scale climate models. The Twin Galaxies function is highly non-isotropic and will be difficult to emulate adequately with a stationary process.…”

Section: Complexity Analysismentioning

confidence: 99%

A localized ensemble of approximate Gaussian processes for fast sequential emulation

Rumsey

Huerta

Tucker

2023

Stat

View full text Add to dashboard Cite

More attention has been given to the computational cost associated with the fitting of an emulator. Substantially less attention is given to the computational cost of using that emulator for prediction. This is primarily because the cost of fitting an emulator is usually far greater than that of obtaining a single prediction, and predictions can often be obtained in parallel. In many settings, especially those requiring Markov Chain Monte Carlo, predictions may arrive sequentially and parallelization is not possible. In this case, using an emulator procedure which can produce accurate predictions efficiently can lead to substantial time savings in practice. In this paper, we propose a global model approximate Gaussian process framework via extension of a popular local approximate Gaussian process (laGP) framework. Our proposed emulator can be viewed as a treed Gaussian process where the leaf nodes are laGP models, and the tree structure is learned greedily as a function of the prediction stream. The suggested method (called leapGP) has interpretable tuning parameters which control the time‐memory trade‐off. One reasonable choice of settings leads to an emulator with a training cost and makes predictions rapidly with an asymptotic amortized cost of .

show abstract

Section: Complexity Analysismentioning

confidence: 99%