Corpus ID: 221557494

Sequential construction and dimension reduction of Gaussian processes under inequality constraints

@article{Bachoc2020SequentialCA,
  title={Sequential construction and dimension reduction of Gaussian processes under inequality constraints},
  author={Franccois Bachoc and Andr'es F. L'opez Lopera and Olivier Roustant},
  journal={arXiv: Statistics Theory},
  year={2020}
}
Accounting for inequality constraints, such as boundedness, monotonicity or convexity, is challenging when modeling costly-to-evaluate black box functions. In this regard, finite-dimensional Gaussian process (GP) models bring a valuable solution, as they guarantee that the inequality constraints are satisfied everywhere. Nevertheless, these models are currently restricted to small dimensional situations (up to dimension 5). Addressing this issue, we introduce the MaxMod algorithm that… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 46 REFERENCES
Finite-dimensional Gaussian approximation with linear inequality constraints
TLDR
The finite-dimensional Gaussian approach from Maatouk and Bay (2017) is considered which can satisfy inequality conditions everywhere and its full framework together with a Hamiltonian Monte Carlo-based sampler provides efficient results on both data fitting and uncertainty quantification. Expand
Gaussian process regression with linear inequality constraints
TLDR
A framework for incorporating any type of linear constraints in Gaussian process modeling is introduced, this including common bound and monotonicity constraints, and a sequential sampling strategy is developed where the input space is explored via a criterion which maximizes the probability of respecting the given constraints. Expand
Bounded Regression with Gaussian Process Projection
Examples with bound information on the regression function and density abound in many real applications. We propose a novel approach for estimating such functions by incorporating the prior knowledgeExpand
Approximating Gaussian Process Emulators with Linear Inequality Constraints and Noisy Observations via MC and MCMC
TLDR
A noise term for the relaxation of the interpolation conditions is introduced, and the corresponding approximation of GP emulators under linear inequality constraints is developed, showing that the performance of MC and MCMC samplers improves when considering noisy observations. Expand
Finite-dimensional approximation of Gaussian processes with inequality constraints
Due to their flexibility, Gaussian processes (GPs) have been widely used in nonparametric function estimation. A prior information about the underlying function is often available. For instance, theExpand
Gaussian process modeling with inequality constraints
TLDR
This paper introduces a new framework for incorporating constraints in Gaussian process modeling, including bound, monotonicity and convexity constraints, and extends this framework to any type of linear constraint. Expand
Gaussian Process Modulated Cox Processes under Linear Inequality Constraints
TLDR
A novel finite approximation of GP-modulated Cox processes where positiveness conditions can be imposed directly on the GP, with no restrictions on the covariance function is introduced. Expand
Kriging of financial term-structures
TLDR
A new term-structure interpolation method that extends classical spline techniques by additionally allowing for quantification of uncertainty by based on a generalization of kriging models with linear equality constraints (market-fit conditions) and shape-preserving conditions such as monotonicity or positivity (no-arbitrage conditions). Expand
Maximum likelihood estimation for Gaussian processes under inequality constraints
We consider covariance parameter estimation for a Gaussian process under inequality constraints (boundedness, monotonicity or convexity) in fixed-domain asymptotics. We address the estimation of theExpand
A supermartingale approach to Gaussian process based sequential design of experiments
Gaussian process (GP) models have become a well-established frameworkfor the adaptive design of costly experiments, and notably of computerexperiments. GP-based sequential designs have been foundExpand
...
1
2
3
4
5
...