[图书][B] Surrogates: Gaussian process modeling, design, and optimization for the applied sciences

RB Gramacy - 2020 - taylorfrancis.com
Computer simulation experiments are essential to modern scientific discovery, whether that
be in physics, chemistry, biology, epidemiology, ecology, engineering, etc. Surrogates are …

Active learning for deep Gaussian process surrogates

A Sauer, RB Gramacy, D Higdon - Technometrics, 2023 - Taylor & Francis
Abstract Deep Gaussian processes (DGPs) are increasingly popular as predictive models in
machine learning for their nonstationary flexibility and ability to cope with abrupt regime …

Traditional kriging versus modern Gaussian processes for large‐scale mining data

RB Christianson, RM Pollyea… - Statistical Analysis and …, 2023 - Wiley Online Library
The canonical technique for nonlinear modeling of spatial/point‐referenced data is known
as kriging in geostatistics, and as Gaussian Process (GP) regression for surrogate modeling …

Vecchia-approximated deep Gaussian processes for computer experiments

A Sauer, A Cooper, RB Gramacy - Journal of Computational and …, 2023 - Taylor & Francis
Abstract Deep Gaussian processes (DGPs) upgrade ordinary GPs through functional
composition, in which intermediate GP layers warp the original inputs, providing flexibility to …

Scaled Vecchia approximation for fast computer-model emulation

M Katzfuss, J Guinness, E Lawrence - SIAM/ASA Journal on Uncertainty …, 2022 - SIAM
Many scientific phenomena are studied using computer experiments consisting of multiple
runs of a computer model while varying the input settings. Gaussian processes (GPs) are a …

Non-stationary Gaussian process surrogates

A Sauer, A Cooper, RB Gramacy - arXiv preprint arXiv:2305.19242, 2023 - arxiv.org
We provide a survey of non-stationary surrogate models which utilize Gaussian processes
(GPs) or variations thereof, including non-stationary kernel adaptations, partition and local …

Generative ai for bayesian computation

NG Polson, V Sokolov - arXiv preprint arXiv:2305.14972, 2023 - arxiv.org
Bayesian Generative AI (BayesGen-AI) methods are developed and applied to Bayesian
computation. BayesGen-AI reconstructs the posterior distribution by directly modeling the …

Locally induced Gaussian processes for large-scale simulation experiments

DA Cole, RB Christianson, RB Gramacy - Statistics and Computing, 2021 - Springer
Gaussian processes (GPs) serve as flexible surrogates for complex surfaces, but buckle
under the cubic cost of matrix decompositions with big training data sizes. Geospatial and …

Active sampling: A machine-learning-assisted framework for finite population inference with optimal subsamples

H Imberg, X Yang, C Flannagan, J Bärgman - Technometrics, 2024 - Taylor & Francis
Data subsampling has become widely recognized as a tool to overcome computational and
economic bottlenecks in analyzing massive datasets. We contribute to the development of …

A comparison of Gaussian processes and neural networks for computer model emulation and calibration

S Myren, E Lawrence - … Analysis and Data Mining: The ASA …, 2021 - Wiley Online Library
Abstract The Department of Energy relies on complex physics simulations for prediction in
domains like cosmology, nuclear theory, and materials science. These simulations are often …