, Finite-dimensional approximation of additive Gaussian processes

, 82 6.2.2 Conditioning to interpolation and inequality constraints 83 6.2.3 Numerical illustrations

. .. Block-additivity, Future, p.89

. .. , Additivity per blocks in 3D, p.91

.. .. Conclusions,

, Contents

, Covariance parameter estimation under inequality constraints

, Asymptotic consistency of maximum likelihood estimators

C. .. Asymptotic,

, Asymptotic normality of maximum likelihood estimators

. .. , Variance parameter estimation, p.105

, Microergodic parameter estimation for the isotropic Matérn model

, 5 2D application: nuclear safety criticality, p.110

.. .. Conclusions,

, 120 8.3.1 Approximation of Gaussian processes in 1D

. .. Cox-process-inference, 123 8.4.1 Metropolis-Hastings algorithm with truncated Gaussian proposals

. .. Applications,

.. .. Conclusions,

. References, Criticality Safety in the Handling of Fissile Material: Specific Safety Guide, International Atomic Energy Agency. IAEA Safety Standards Series, 2014.

M. Abramowitz and I. A. Stegun, Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables, 1964.

R. P. Adams, I. Murray, and D. J. Mackay, Tractable nonparametric Bayesian inference in Poisson processes with Gaussian process intensities, International Conference on Machine Learning, pp.9-16, 2009.

R. J. Adler, An Introduction to Continuity, Extrema, and Related Topics for General Gaussian Processes, IMS, 1990.

R. J. Adler and J. E. Taylor, Random Fields and Geometry, 2007.
URL : https://hal.archives-ouvertes.fr/hal-01975050

J. Azaïs and M. Wschebor, Level Sets and Extrema of Random Processes and Fields, 2009.

D. Azzimonti, profExtrema: Compute and Visualize Profile Extrema Functions, 2018.

D. Azzimonti, D. Ginsbourger, J. Rohmer, and D. Idier, Profile extrema for visualizing and quantifying uncertainties on excursion regions. Application to coastal flooding, Technometrics, vol.0, pp.1-26, 2019.
URL : https://hal.archives-ouvertes.fr/hal-02127924

F. Bachoc, Cross validation and maximum likelihood estimations of hyperparameters of Gaussian processes with model misspecification, Computational Statistics & Data Analysis, vol.66, pp.55-69, 2013.

F. Bachoc, A. Lagnoux, and A. F. López-lopera, Maximum likelihood estimation for Gaussian processes under inequality constraints, Electronic Journal of Statistics, vol.13, issue.2, pp.2921-2969, 2019.
URL : https://hal.archives-ouvertes.fr/hal-01864340

A. Baddeley, P. Gregori, J. Mahiques, R. Stoica, and D. Stoyan, Case Studies in Spatial Point Process Modeling, Lecture Notes in Statistics, 2006.

A. Baddeley, E. Rubak, and R. Turner, Spatial Point Patterns: Methodology and Applications with R. Chapman & Hall/CRC Interdisciplinary Statistics, 2015.

C. B. Barber, D. P. Dobkin, and H. Huhdanpaa, The quickhull algorithm for convex hulls, ACM Transactions on Mathematical Software, vol.22, issue.4, pp.469-483, 1996.

X. Bay, L. Grammont, and H. Maatouk, Generalization of the Kimeldorf-Wahba correspondence for constrained interpolation, Electronic journal of statistics, vol.10, issue.1, pp.1580-1595, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01270237

J. Bect, F. Bachoc, and D. Ginsbourger, A supermartingale approach to Gaussian process based sequential design of experiments, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01351088

Z. I. Botev, The normal law under linear restrictions: Simulation and estimation via minimax tilting, Journal of the Royal Statistical Society: Series B, vol.79, issue.1, pp.125-148, 2017.

S. Brenner and R. Scott, The Mathematical Theory of Finite Element Methods, Texts in Applied Mathematics, 2007.

S. Brooks, A. Gelman, G. Jones, and X. Meng, Handbook of Markov Chain Monte Carlo. Chapman & Hall/CRC Handbooks of Modern Statistical Methods, 2011.

A. Buja, T. Hastie, and R. Tibshirani, Linear smoothers and additive models, The Annals of Statistics, vol.17, issue.2, pp.453-510, 1989.

J. Cha and M. Finkelstein, Point Processes for Reliability Analysis: Shocks and Repairable Systems, Springer Series in Reliability Engineering, 2018.

A. Cousin, H. Maatouk, and D. Rullière, Kriging of financial term-structures, European Journal of Operational Research, vol.255, issue.2, pp.631-648, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01206388

D. R. Cox, Some statistical methods connected with series of events, Journal of the Royal Statistical Society: Series B, vol.17, issue.2, pp.129-164, 1955.

J. Creutzig, T. Müller-gronbach, and K. Ritter, Free-knot spline approximation of stochastic processes, Journal of Complexity, vol.23, issue.4, pp.867-889, 2007.

S. Da-veiga and A. Marrel, Gaussian process modeling with inequality constraints. Annales de la faculté des sciences de, Toulouse Mathématiques, vol.21, issue.3, pp.529-555, 2012.

C. De-boor, A Practical Guide to Splines, Applied Mathematical Sciences, 2001.

C. De-boor, Spline basics, Handbook of Computer Aided Geometric Design, pp.141-163, 2002.

J. De-loera, J. Rambau, and F. Santos, Triangulations: Structures for Algorithms and Applications. Algorithms and Computation in Mathematics, 2010.

B. Delaunay, Sur la sphère vide. A la mémoire de Georges Voronoï, Bulletin de l'Académie des Sciences de l'URSS, issue.6, pp.793-800, 1934.

Y. Deville, D. Ginsbourger, and O. Roustant, kergp: Gaussian Process Laboratory, 2015.
URL : https://hal.archives-ouvertes.fr/emse-01169696

P. J. Diggle, P. Moraga, B. Rowlingson, and B. M. Taylor, Spatial and spatio-temporal log-Gaussian Cox processes: Extending the geostatistical paradigm, Statistical Science, vol.28, issue.4, pp.542-563, 2013.

C. Donner and M. Opper, Efficient Bayesian inference of sigmoidal Gaussian Cox processes, Journal of Machine Learning Research, vol.19, issue.67, pp.1-34, 2018.

J. Du, H. Zhang, and V. S. Mandrekar, Fixed-domain asymptotic properties of tapered maximum likelihood estimators, The Annals of Statistics, vol.37, issue.6A, pp.3330-3361, 2009.

S. Duane, A. D. Kennedy, B. J. Pendleton, and D. Roweth, Hybrid Monte Carlo, Physics letters B, vol.195, issue.2, pp.216-222, 1987.

D. Dupuy, C. Helbert, and J. Franco, DiceDesign and DiceEval: Two R packages for design and analysis of computer experiments, Journal of Statistical Software, vol.65, issue.11, pp.1-38, 2015.
URL : https://hal.archives-ouvertes.fr/hal-02065877

N. Durrande, V. Adam, L. Bordeaux, S. Eleftheriadis, and J. Hensman, Banded matrix operators for Gaussian Markov models in the automatic differentiation era, International Conference on Artificial Intelligence and Statistics, pp.2780-2789, 2019.

N. Durrande, D. Ginsbourger, and O. Roustant, Additive covariance kernels for high-dimensional Gaussian process modeling, vol.21, pp.481-499, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00644934

D. K. Duvenaud, H. Nickisch, and C. E. Rasmussen, Additive Gaussian processes, Advances in Neural Information Processing Systems, pp.226-234, 2011.

T. Fernandez, N. Rivera, and Y. W. Teh, Gaussian processes for survival analysis, Conference on Neural Information Processing Systems, pp.5021-5029, 2016.

F. Fernex, L. Heulers, O. Jacquet, J. Miss, and Y. Richet, The MORET 4B Monte Carlo code -New features to treat complex criticality systems, M&C international conference on mathematics and computation supercomputing, reactor physics and nuclear and biological application, vol.59, 2005.

S. Flaxman, A. Wilson, D. Neill, H. Nickisch, and A. Smola, Fast Kronecker inference in Gaussian processes with non-Gaussian likelihoods, Proceedings of Machine Learning Research, pp.607-616, 2015.

J. M. Flegal, J. Hughes, D. Vats, and N. Dai, mcmcse: Monte Carlo Standard Errors for MCMC, 2017.

J. Fruth, Sensitivy analysis and graph-based methods for black-box functions with on application to sheet metal forming. Theses, 2015.
URL : https://hal.archives-ouvertes.fr/tel-01151170

J. Fruth, O. Roustant, and S. Kuhnt, Total interaction index: A variance-based sensitivity index for second-order interaction screening, Journal of Statistical Planning and Inference, vol.147, pp.212-223, 2014.
URL : https://hal.archives-ouvertes.fr/hal-00631066

M. G. Genton, Classes of kernels for machine learning: A statistics perspective, Journal of Machine Learning Research, vol.2, pp.299-312, 2001.

A. Genz, Numerical computation of multivariate normal probabilities, Journal of Computational and Graphical Statistics, vol.1, pp.141-150, 1992.

C. J. Geyer, Practical Markov Chain Monte Carlo, Statistical Science, vol.7, issue.4, pp.473-483, 1992.

S. Golchi, D. R. Bingham, H. Chipman, and D. A. Campbell, , 2015.

, Monotone emulation of computer experiments, SIAM/ASA Journal on Uncertainty Quantification, vol.3, issue.1, pp.370-392

D. Goldfarb and A. Idnani, Dual and primal-dual methods for solving strictly convex quadratic programs, Numerical Analysis, pp.226-239, 1982.

R. Goldman, B-spline approximation and the de Boor algorithm, Pyramid Algorithms, pp.347-443, 2003.

L. Gong and J. M. Flegal, A practical sequential stopping rule for highdimensional Markov Chain Monte Carlo, Journal of Computational and Graphical Statistics, vol.25, issue.3, pp.684-700, 2016.

T. Gunter, C. M. Lloyd, M. A. Osborne, and S. J. Roberts, Efficient Bayesian nonparametric modelling of structured point processes, Conference on Uncertainty in Artificial Intelligence, pp.310-319, 2014.

T. Hastie and R. Tibshirani, Generalized additive models, Statistical Science, vol.1, issue.3, pp.297-310, 1986.

J. Hensman, N. Durrande, and A. Solin, Variational Fourier features for Gaussian processes, Journal of Machine Learning Research, vol.18, issue.1, pp.5537-5588, 2017.
URL : https://hal.archives-ouvertes.fr/emse-01411206

J. Hensman, N. Fusi, and N. D. Lawrence, Gaussian processes for big data, Conference on Uncertainty in Artificial Intelligence, pp.282-290, 2013.

Y. Hu, An algorithm for data reduction using splines with free knots, IMA Journal of Numerical Analysis, vol.13, issue.3, pp.365-381, 1993.

R. J. Hyndman and Y. Fan, Sample quantiles in statistical packages, The American Statistician, vol.50, issue.4, pp.361-365, 1996.

I. Ibragimov and Y. Rozanov, Gaussian Random Processes, 1978.

S. John and J. Hensman, Large-scale Cox process inference using variational Fourier features, Proceedings of Machine Learning Research, pp.2362-2370, 2018.

S. G. Johnson, The NLopt nonlinear-optimization package

D. R. Jones, M. Schonlau, and W. J. Welch, Efficient global optimization of expensive black-box functions, Journal of Global Optimization, vol.13, issue.4, pp.455-492, 1998.

D. Jupp, Approximation to data by splines with free knots, SIAM Journal on Numerical Analysis, vol.15, issue.2, pp.328-343, 1978.

O. Kallenberg, Foundations of Modern Probability. Probability and its Applications, 2002.

C. Kaufman and B. Shaby, The role of the range parameter for estimation and prediction in geostatistics, Biometrika, vol.100, pp.473-484, 2013.

J. Kingman, Poisson Processes. Oxford Studies in Probability, 1992.

L. P. Kobbelt, Multiresolution techniques, Handbook of Computer Aided Geometric Design, pp.343-361, 2002.

J. Kocijan, Modelling and Control of Dynamic Systems using Gaussian Process Models. Advances in Industrial Control, 2016.

Y. Kozachenko, O. Pogorilyak, I. Rozora, and A. Tegza, Simulation of Cox random processes, Simulation of Stochastic Processes with Given Accuracy and Reliability, pp.251-304, 2016.

S. Lan and B. Shahbaba, Sampling constrained probability distributions using spherical augmentation, Algorithmic Advances in Riemannian Geometry and Applications, pp.25-71, 2016.

T. A. Lasko, Efficient inference of Gaussian-process-modulated renewal processes with application to medical event data, Uncertainty in artificial intelligence, pp.469-476, 2014.

D. T. Lee and B. J. Schachter, Two algorithms for constructing a Delaunay triangulation, International Journal of Computer & Information Sciences, vol.9, issue.3, pp.219-242, 1980.

W. V. Li and W. Linde, Approximation, metric entropy and small ball estimates for Gaussian measures, The Annals of Probability, vol.27, issue.3, pp.1556-1578, 1999.

C. M. Lloyd, T. Gunter, M. A. Osborne, and S. J. Roberts, Variational inference for Gaussian process modulated Poisson processes, International Conference on Machine Learning, pp.1814-1822, 2015.

W. L. Loh, Fixed-domain asymptotics for a subclass of Matérn-type Gaussian random fields, The Annals of Statistics, vol.33, issue.5, pp.2344-2394, 2005.

W. L. Loh and T. K. Lam, Estimating structured correlation matrices in smooth Gaussian random field models, The Annals of Statistics, vol.28, issue.3, pp.880-904, 2000.

A. F. López-lopera, lineqGPR: Gaussian Process Regression Models with Linear Inequality Constraints, 2019.

A. F. López-lopera, F. Bachoc, N. Durrand-e, J. Rohmer, D. Idier et al., Approximating Gaussian process emulators with linear inequality constraints and noisy observations via MC and MCMC, 2019.

A. F. López-lopera, F. Bachoc, N. Durrande, and O. Roustant, Finitedimensional Gaussian approximation with linear inequality constraints, SIAM/ASA Journal on Uncertainty Quantification, vol.6, issue.3, pp.1224-1255, 2018.

A. F. López-lopera, S. John, and N. Durrande, Gaussian process modulated Cox processes under linear inequality constraints, International Conference on Artificial Intelligence and Statistics, pp.1997-2006, 2019.

H. Maatouk, Correspondance entre régression par processus gaussien et splines d'interpolation sous contraintes linéaires de type inégalité, 2015.

H. Maatouk, Finite-dimensional approximation of Gaussian processes with inequality constraints, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01533356

H. Maatouk and X. Bay, A new rejection sampling method for truncated multivariate Gaussian random variables restricted to convex sets, Monte Carlo and Quasi-Monte Carlo Methods, pp.521-530, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01063978

H. Maatouk and X. Bay, Gaussian process emulators for computer experiments with inequality constraints, Mathematical Geosciences, vol.49, issue.5, pp.557-582, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01096751

H. Maatouk, O. Roustant, and Y. Richet, Cross-validation estimations of hyperparameters of Gaussian processes with inequality constraints, Procedia Environmental Sciences, vol.27, pp.38-44, 2015.
URL : https://hal.archives-ouvertes.fr/emse-01185753

I. Macdonald, Symmetric Functions and Hall Polynomials, 1998.

C. D. Meyer, Matrix Analysis and Applied Linear Algebra, Society for Industrial and Applied Mathematics, 2000.

J. Møller, A. R. Syversveen, and R. P. Waagepetersen, Log Gaussian Cox processes, Scandinavian Journal of Statistics, vol.25, issue.3, pp.451-482, 2001.

J. Møller and R. P. Waagepetersen, Statistical Inference and Simulation for Spatial Point Processes. Chapman & Hall/CRC Monographs on Statistics and Applied Probability, 2004.

T. Muehlenstaedt, O. Roustant, L. Carraro, and S. Kuhnt, Data-driven Kriging models based on FANOVA-decomposition, Statistics and Computing, vol.22, issue.3, pp.723-738, 2012.
URL : https://hal.archives-ouvertes.fr/emse-00699673

J. Munkres, Elements Of Algebraic Topology, 2018.

K. P. Murphy, Machine Learning: A Probabilistic Perspective (Adaptive Computation and Machine Learning Series, 2012.

R. M. Neal, Bayesian Learning for Neural Networks, 1996.

H. Nickisch and C. E. Rasmussen, Approximations for binary Gaussian process classification, Journal of Machine Learning Research, vol.9, pp.2035-2078, 2008.

A. Okabe, B. Boots, and K. Sugihara, Spatial Tessellations: Concepts and Applications of Voronoi Diagrams, 1992.

C. J. Paciorek and M. J. Schervish, Nonstationary covariance functions for Gaussian process regression, Conference on Neural Information Processing Systems, pp.273-280, 2004.

A. Pakman and L. Paninski, Exact Hamiltonian Monte Carlo for truncated multivariate Gaussians, Journal of Computational and Graphical Statistics, vol.23, issue.2, pp.518-542, 2014.

C. Pan and M. Zhu, Group additive structure identification for kernel nonparametric regression, Advances in Neural Information Processing Systems, pp.4907-4916, 2017.

W. H. Press, S. A. Teukolsky, W. T. Vetterling, and B. P. Flannery, Numerical Recipes in C: The Art of Scientific Computing, 1992.

L. Pronzato, Minimax and maximin space-filling designs: Some properties and methods for construction, Journal de la Société Française de Statistique, vol.158, issue.1, pp.7-36, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01496712

L. Pronzato and W. G. Müller, Design of computer experiments: filling and beyond, Statistics and Computing, vol.22, issue.3, pp.681-701, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00685876

J. Quiñonero-candela and C. E. Rasmussen, A unifying view of sparse approximate gaussian process regression, Journal of Machine Learning Research, vol.6, pp.1939-1959, 2005.

. R-core-team, R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, 2018.

C. E. Rasmussen and C. K. Williams, Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning), 2005.

P. Ray, D. Pati, and A. Bhattacharya, Efficient Bayesian shape-restricted function estimation with constrained Gaussian process priors, 2019.

J. Riihimäki and A. Vehtari, Gaussian processes with monotonicity information, Journal of Machine Learning Research: Workshop and Conference Proceedings, pp.645-652, 2010.

B. D. Ripley, Modelling spatial patterns, Journal of the Royal Statistical Society: Series B, vol.39, issue.2, pp.172-212, 1977.

J. Rohmer and D. Idier, A meta-modelling strategy to identify the critical offshore conditions for coastal flooding, Natural Hazards and Earth System Sciences, vol.12, issue.9, pp.2943-2955, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00733495

O. Roustant, D. Ginsbourger, and Y. Deville, DiceKriging, DiceOptim: Two R packages for the analysis of computer experiments by Kriging-based metamodeling and optimization, Journal of Statistical Software, vol.51, issue.1, pp.1-55, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00495766

T. Santner, B. Williams, and W. Notz, The Design and Analysis of Computer Experiments, 2003.

T. Santner, B. Williams, and W. Notz, Space-filling designs for computer experiments, The Design and Analysis of Computer Experiments, pp.121-161, 2003.

S. Särkkä, Bayesian Filtering and Smoothing, 2013.

R. Serfozo, Renewal and regenerative processes, Basics of Applied Stochastic Processes, pp.99-167, 2009.

M. Slassi, The optimal free knot spline approximation of stochastic differential equations with additive noise, Journal of Computational and Applied Mathematics, vol.261, pp.62-71, 2014.

L. A. Sleeper and D. P. Harrington, Regression splines in the Cox model with application to covariate effects in liver disease, Journal of the American Statistical Association, vol.85, issue.412, pp.941-949, 1990.

E. Snelson and Z. Ghahramani, Sparse Gaussian processes using pseudo-inputs, Advances in Neural Information Processing Systems, pp.1257-1264, 2006.

M. Stein, Interpolation of Spatial Data: Some Theory for Kriging, Springer Series in Statistics, 1999.

K. Svanberg, A class of globally convergent optimization methods based on conservative convex separable approximations, SIAM Journal on Optimization, vol.12, issue.2, pp.555-573, 2002.

J. Taylor and Y. Benjamini, RestrictedMVN: Multivariate Normal Restricted by Affine Constraints, 2016.

Y. W. Teh and V. Rao, Gaussian process modulated renewal processes, Advances in Neural Information Processing Systems, pp.2474-2482, 2011.

M. Titsias, Variational learning of inducing variables in sparse Gaussian processes, International Conference on Artificial Intelligence and Statistics, pp.567-574, 2009.

R. Turner, deldir: Delaunay Triangulation and Dirichlet (Voronoi) Tessellation. R package version 0, pp.1-15, 2018.

A. W. Van-der-vaart, Asymptotic Statistics, vol.3, 1998.

M. Van-der-wilk, C. E. Rasmussen, and J. Hensman, Convolutional Gaussian processes, Conference on Neural Information Processing Systems, pp.2845-2854, 2017.

J. Vanhatalo and A. Vehtari, Sparse log Gaussian processes via MCMC for spatial epidemiology, Proceedings of Machine Learning Research, pp.73-89, 2007.

D. Vats, J. M. Flegal, and G. L. Jones, Multivariate output analysis for Markov Chain Monte Carlo, 2017.

M. I. Yadrenko, Spectral Theory of Random Fields. Translation series in mathematics and engineering. Optimization Software, 1983.

N. Yannaros, On Cox processes and Gamma renewal processes, Journal of Applied Probability, vol.25, issue.2, pp.423-427, 1988.

N. Yannaros, Weibull renewal processes, Annals of the Institute of Statistical Mathematics, vol.46, issue.4, pp.641-648, 1994.

Z. Ying, Maximum likelihood estimation of parameters under a spatial sampling scheme, The Annals of Statistics, vol.21, issue.3, pp.1567-1590, 1993.

H. Zhang, Inconsistent estimation and asymptotically equal interpolations in model-based geostatistics, Journal of the American Statistical Association, vol.99, issue.465, pp.250-261, 2004.

J. Zhang and L. Lin, Bounded regression with Gaussian process projection, 2018.

S. Zhou, P. Giulani, J. Piekarewicz, A. Bhattacharya, and D. Pati, Reexamining the proton-radius problem using constrained Gaussian processes, Physical Review C, vol.99, p.55202, 2019.

O. Zienkiewicz, R. Taylor, and J. Zhu, The Finite Element Method: Its Basis and Fundamentals. The Finite Element Method, 2013.

A. Felipe and L. , Modélisation par Processus Gaussiens sous Contraintes d'Inégalité Spécialité : Mathématiques Appliquées Mots clefs : Méthodes d'Inférence Bayésienne, Processus Gaussiens, Métamodélisation sous Contraintes d'Inégalité

, Nous remarquons que l'introduction d'un bruit d'observations permet de monterà la dimension cinq. Nous proposons un algorithme d'insertion des noeuds, qui concentre le budget de calcul sur les dimensions les plus actives. Nous explorons aussi la triangulation de Delaunay comme alternativeà la tensorisation. Enfin, nousétudions l'utilisation de modèles additifs dans ce contexte, théoriquement et sur des problèmes de plusieurs centaines de variables. Troisièmement, nous donnons des résultats théoriques sur l'inférence sous contraintes d'inégalité. La consistance et la normalité asymptotique d'estimateurs par maximum de vraisemblance sontétablies. L'ensemble des travaux a fait l'objet d'un développement logiciel en R. Ils sont appliquésà des problèmes de gestion des risques en sûreté nucléaire et inondations côtières, Le conditionnement de Processus Gaussiens (PG) par des contraintes d'inégalité permet d'obtenir des modèles plus réalistes. Cette thèse s'intéresse au modèle de type PG proposé par Maatouk, 2015.