score

Calculates score, proportional to the multivariate normal log
 likelihood. Higher scores indicate better fits. Only 
 applicable to noisy data. Requires full covariance matrix 
 (e.g. <code>predict</code> with <code>lite = FALSE</code>).

Performs Bayesian posterior inference for deep Gaussian processes
following Sauer, Gramacy, and Higdon (2023, <doi:10.48550/arXiv.2012.08015>). See Sauer
(2023, <http://hdl.handle.net/10919/114845>) for comprehensive methodological
details and <https://bitbucket.org/gramacylab/deepgp-ex/> for a variety of
coding examples. Models are trained through MCMC including elliptical
slice sampling of latent Gaussian layers and Metropolis-Hastings
sampling of kernel hyperparameters. Vecchia-approximation for faster
computation is implemented following Sauer, Cooper, and Gramacy
(2023, <doi:10.48550/arXiv.2204.02904>). Optional monotonic warpings are implemented
following Barnett et al. (2024, <doi:10.48550/arXiv.2408.01540>). Downstream tasks include sequential design
through active learning Cohn/integrated mean squared error
(ALC/IMSE; Sauer, Gramacy, and Higdon, 2023), optimization through
expected improvement (EI; Gramacy, Sauer, and Wycoff, 2022 <doi:10.48550/arXiv.2112.07457>),
and contour location through entropy
(Booth, Renganathan, and Gramacy, 2024 <doi:10.48550/arXiv.2308.04420>). Models
extend up to three layers deep; a one layer model is equivalent to typical
Gaussian process regression. Incorporates OpenMP and SNOW parallelization
and utilizes C/C++ under the hood.

Annie Booth

deepgp

Bayesian Deep Gaussian Processes using MCMC

score function

<dl><dt>y</dt>
<dd>response vector</dd>
<dt>mu</dt>
<dd>predicted mean</dd>
<dt>sigma</dt>
<dd>predicted covariance</dd></dl>

Arguments

Calculates score — score

<dl>

<dt>y</dt>
<dd>response vector</dd>


<dt>mu</dt>
<dd>predicted mean</dd>


<dt>sigma</dt>
<dd>predicted covariance</dd>

</dl>

score: Calculates score

Description

Usage

Arguments

References

Examples