• Corpus ID: 211010677

Classification of Computer Models with Labelled Outputs

@article{Kimpton2020ClassificationOC,
  title={Classification of Computer Models with Labelled Outputs},
  author={Louise Kimpton and Peter Challenor and Daniel Williamson},
  journal={arXiv: Methodology},
  year={2020}
}
Classification is a vital tool that is important for modelling many complex numerical models. A model or system may be such that, for certain areas of input space, the output either does not exist, or is not in a quantifiable form. Here, we present a new method for classification where the model outputs are given distinct classifying labels, which we model using a latent Gaussian process (GP). The latent variable is estimated using MCMC sampling, a unique likelihood and distinct prior… 

References

SHOWING 1-10 OF 26 REFERENCES
Approximations for Binary Gaussian Process Classification
We provide a comprehensive overview of many recent algorithms for approximate inference in Gaussian process models for probabilistic binary classification. The relationships between several
Bayesian Calibration of computer models
TLDR
A Bayesian calibration technique which improves on this traditional approach in two respects and attempts to correct for any inadequacy of the model which is revealed by a discrepancy between the observed data and the model predictions from even the best‐fitting parameter values is presented.
Screening, predicting, and computer experiments
TLDR
This work model the output of the computer code as the realization of a stochastic process, allowing nonlinear and interaction effects to emerge without explicitly modeling such effects.
Approximate Bayesian computation (ABC) gives exact results under the assumption of model error
  • R. Wilkinson
  • Computer Science
    Statistical applications in genetics and molecular biology
  • 2013
TLDR
Under the assumption of the existence of a uniform additive model error term, ABC algorithms give exact results when sufficient summaries are used, which allows the approximation made in many previous application papers to be understood, and should guide the choice of metric and tolerance in future work.
Bayesian History Matching of Complex Infectious Disease Models Using Emulation: A Tutorial and a Case Study on HIV in Uganda
TLDR
A novel method that has the potential to improve the calibration of complex infectious disease models (hereafter called simulators) is presented in the form of a tutorial and a case study where the history match a dynamic, event-driven, individual-based stochastic HIV simulator is used, using extensive demographic, behavioural and epidemiological data available from Uganda.
Multivariate Generalized Gaussian Process Models
TLDR
By instantiating the EFD with specific parameter functions, this work obtains two novel GP models (and corresponding inference algorithms) for correlated outputs: a Von-Mises GP for angle regression; and a Dirichlet GP for regressing on the multinomial simplex.
Uncertainty Quantification for Computer Models With Spatial Output Using Calibration-Optimal Bases
TLDR
A simple test to allow a practitioner to establish whether their experiment will result in a terminal case analysis, and a methodology for defining calibration-optimal bases that avoid this whenever it is not inevitable are presented.
Galaxy formation : a Bayesian uncertainty analysis.
TLDR
A Bayes Linear approach is presented in order to identify the subset of the input space that could give rise to acceptable matches between model output and measured data, and was successful in producing a large collection of model evaluations that exhibit good fits to the observed data.
Model-based Geostatistics
Conventional geostatistical methodology solves the problem of predicting the realized value of a linear functional of a Gaussian spatial stochastic process S(x) based on observations Yi = S(xi) + Zi
...
1
2
3
...