Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
134 tokens/sec
GPT-4o
9 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A graphical multi-fidelity Gaussian process model, with application to emulation of heavy-ion collisions (2108.00306v5)

Published 31 Jul 2021 in stat.ME

Abstract: With advances in scientific computing and mathematical modeling, complex scientific phenomena such as galaxy formations and rocket propulsion can now be reliably simulated. Such simulations can however be very time-intensive, requiring millions of CPU hours to perform. One solution is multi-fidelity emulation, which uses data of different fidelities to train an efficient predictive model which emulates the expensive simulator. For complex scientific problems and with careful elicitation from scientists, such multi-fidelity data may often be linked by a directed acyclic graph (DAG) representing its scientific model dependencies. We thus propose a new Graphical Multi-fidelity Gaussian Process (GMGP) model, which embeds this DAG structure (capturing scientific dependencies) within a Gaussian process framework. We show that the GMGP has desirable modeling traits via two Markov properties, and admits a scalable algorithm for recursive computation of the posterior mean and variance along at each depth level of the DAG. We also present a novel experimental design methodology over the DAG given an experimental budget, and propose a nonlinear extension of the GMGP via deep Gaussian processes. The advantages of the GMGP are then demonstrated via a suite of numerical experiments and an application to emulation of heavy-ion collisions, which can be used to study the conditions of matter in the Universe shortly after the Big Bang. The proposed model has broader uses in data fusion applications with graphical structure, which we further discuss.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (63)
  1. Optimal sliced Latin hypercube designs. Technometrics, 57(4):479–487.
  2. Bayesian estimation of the specific shear and bulk viscosity of quark–gluon plasma. Nature Physics, 15(11):1113–1117.
  3. Distributed data fusion: neighbors, rumors, and the art of collective knowledge. IEEE Control Systems Magazine, 36(4):83–109.
  4. An evaluation of RANS turbulence modelling for aerodynamic applications. Aerospace Science and Technology, 7(7):493–509.
  5. Function-on-function kriging, with applications to three-dimensional printing of aortic tissues. Technometrics, 63(3):384–395.
  6. Single-particle distribution in the hydrodynamic and statistical thermodynamic models of multiparticle production. Physical Review D, 10(1):186.
  7. Deep Gaussian processes for multi-fidelity modeling. arXiv preprint arXiv:1903.07320.
  8. Deep Gaussian processes. In Artificial Intelligence and Statistics, pages 207–215. PMLR.
  9. BdryGP: a new Gaussian process model for incorporating boundary information. arXiv preprint arXiv:1908.08868.
  10. An adaptive strategy for sequential designs of multilevel computer experiments. International Journal for Uncertainty Quantification, 13(4).
  11. Phenomenological constraints on the transport properties of QCD matter with data-driven model averaging. Physical Review Letters, 126(24):242301.
  12. Multisystem Bayesian constraints on the transport coefficients of QCD matter. Physical Review C, 103(5):054904.
  13. Number-Theoretic Methods in Statistics. CRC Press.
  14. Engineering Design via Surrogate Modelling: A Practical Guide. John Wiley & Sons.
  15. Friedman, J. H. (1991). Multivariate adaptive regression splines. The Annals of Statistics, pages 1–67.
  16. Giles, M. B. (2008). Multilevel monte carlo path simulation. Operations research, 56(3):607–617.
  17. Gaussian process priors with uncertain inputs - application to multiple-step ahead time series forecasting. Advances in Neural Information Processing Systems, 15:545–552.
  18. Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association, 102(477):359–378.
  19. Monotone emulation of computer experiments. SIAM/ASA Journal on Uncertainty Quantification, 3(1):370–392.
  20. MFNets: learning network representations for multifidelity surrogate modeling. arXiv preprint arXiv:2008.02672.
  21. MFNets: multi-fidelity data-driven networks for Bayesian learning and prediction. International Journal for Uncertainty Quantification, 10(6).
  22. Gramacy, R. B. (2020). Surrogates: Gaussian Process Modeling, Design, and Optimization for the Applied Sciences. CRC press.
  23. Cell adhesion molecules and their roles and regulation in the immune and tumor microenvironment. Frontiers in Immunology, 10:1078.
  24. Multifidelity emulation for the matter power spectrum using Gaussian processes. Monthly Notices of the Royal Astronomical Society, 509(2):2551–2565.
  25. Remark on algorithm 659: Implementing Sobol’s quasirandom sequence generator. ACM Transactions on Mathematical Software (TOMS), 29(1):49–57.
  26. Minimax and maximin distance designs. Journal of Statistical Planning and Inference, 26(2):131–148.
  27. Predicting the output from a complex computer code when fast approximations are available. Biometrika, 87(1):1–13.
  28. Flexible sliced designs for computer experiments. Annals of the Institute of Statistical Mathematics, 70:631–646.
  29. Bayesian analysis of multifidelity computer models with local features and nonnested experimental designs: application to the WRF model. Technometrics, 63(4):510–522.
  30. Combinatorial Optimization, volume 1. Springer.
  31. Le Gratiet, L. (2012). MuFiCokriging: multi-fidelity cokriging models. R package version 1.2.
  32. Recursive co-kriging model for design of computer experiments with multiple levels of fidelity. International Journal for Uncertainty Quantification, 4(5):365–386.
  33. Data fusion with multi-fidelity Gaussian processes for aerodynamic experimental and numerical databases. In SIAM Conference on Computational Science and Engineering (CSE).
  34. Ma, P. (2020). Objective Bayesian analysis of a cokriging model for hierarchical multifidelity codes. SIAM/ASA Journal on Uncertainty Quantification, 8(4):1358–1382.
  35. Multifidelity computer model emulation with high-dimensional output: An application to storm surge. Journal of the Royal Statistical Society Series C: Applied Statistics, 71(4):861–883.
  36. Minimax and minimax projection designs using clustering. Journal of Computational and Graphical Statistics, 27(1):166–178.
  37. An efficient surrogate model for emulation and physics extraction of large eddy simulations. Journal of the American Statistical Association, 113(524):1443–1456.
  38. Algorithms and Data Structures: The Basic Toolbox, volume 55. Springer.
  39. Alternative ansatz to wounded nucleon and binary collision scaling in high-energy nuclear collisions. Physical Review C, 92(1):011901.
  40. Exploratory designs for computational experiments. Journal of Statistical Planning and Inference, 43(3):381–402.
  41. Numerical Optimization. Springer Science & Business Media.
  42. Determining fundamental properties of matter created in ultrarelativistic heavy-ion collisions. Physical Review C, 89(3):034917.
  43. Okuda, H. (1972). Nonphysical noises and instabilities in plasma simulation due to a spatial grid. Journal of Computational Physics, 10(3):475–486.
  44. O’Hagan, A. (1998). A Markov property for covariance structures. Technical report, University of Nottingham.
  45. Nonlinear information fusion algorithms for data-efficient multi-fidelity modelling. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 473(2198):20160751.
  46. Multi-fidelity machine learning models for accurate bandgap predictions of solids. Computational Materials Science, 129:156–163.
  47. Pope, S. B. (2000). Turbulent Flows. Cambridge University Press.
  48. Pronzato, L. (2017). Minimax and maximin space-filling designs: some properties and methods for construction. Journal de la Société Française de Statistique, 158(1):7–36.
  49. Qian, P. Z. G. (2012). Sliced Latin hypercube designs. Journal of the American Statistical Association, 107(497):393–399.
  50. Artificial Intelligence: A Modern Approach. Prentice Hall, second edition.
  51. The Design and Analysis of Computer Experiments. Springer.
  52. Stephenson, T. A. (2000). An introduction to Bayesian network theory and usage. Technical report, IDIAP.
  53. Calibration for computer experiments with binary responses and application to cell adhesion study. Journal of the American Statistical Association, 115(532):1664–1674.
  54. Stacking designs: designing multi-fidelity computer experiments with confidence. arXiv preprint arXiv:2211.00268.
  55. Wang, X. (2016). Swirling fluid mixing and combustion dynamics at supercritical conditions. PhD thesis, Georgia Institute of Technology.
  56. Estimating shape constrained functions using Gaussian processes. SIAM/ASA Journal on Uncertainty Quantification, 4(1):1–25.
  57. Screening, predicting, and computer experiments. Technometrics, 34(1):15–25.
  58. Wendland, H. (2004). Scattered Data Approximation, volume 17. Cambridge University Press.
  59. Local error estimates for radial basis function interpolation of scattered data. IMA Journal of Numerical Analysis, 13(1):13–27.
  60. Networked data fusion with packet losses and variable delays. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 39(5):1107–1120.
  61. GraphRNN: Generating realistic graphs with deep auto-regressive models. In International Conference on Machine Learning, pages 5708–5717. PMLR.
  62. D-VAE: A variational autoencoder for directed acyclic graphs. Advances in Neural Information Processing Systems, 32.
  63. Gaussian process subspace regression for model reduction. arXiv preprint arXiv:2107.04668.
Citations (11)

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com