Predictive approaches for choosing hyperparameters in Gaussian processes
Gaussian processes are powerful regression models specified by parameterized mean and covariance functions. Standard approaches to choose these parameters (known by the name hyperparameters) are maximum likelihood and maximum a posteriori. In this article, we propose and investigate predictive approaches based on Geisser's predictive sample reuse (PSR) methodology and the related Stone's cross-validation (CV) methodology. More specifically, we derive results for Geisser's surrogate predictive probability (GPP), Geisser's predictive mean square error (GPE), and the standard CV error and make a comparative study. Within an approximation we arrive at the generalized cross-validation (GCV) and establish its relationship with the GPP and GPE approaches. These approaches are tested on a number of problems. Experimental results show that these approaches are strongly competitive with the existing approaches.
- A comparative study of ordinary cross-validation, v-fold cross-validation and the repeated learning-testing methods
- A Predictive Approach to Model Selection
- Multivariate adaptive regression splines
- Smoothing noisy data with spline functions: Estimating the correct degree of smoothing by the method of generalized cross-validation
- The Predictive Sample Reuse Method with Applications
- Efficient approximate leave-one-out cross-validation for kernel logistic regression
- A flexible approach to inference in semiparametric regression models with correlated errors using Gaussian processes
- Nested polynomial trends for the improvement of Gaussian process-based predictors
- Cross validation and maximum likelihood estimations of hyper-parameters of Gaussian processes with model misspecification
- A survey of Bayesian predictive methods for model assessment, selection and comparison
- Efficient leave-one-out cross-validation for Bayesian non-factorized normal and Student-t models
- A fast and calibrated computer model emulator: an empirical Bayes approach
- Deterministic global optimization with Gaussian processes embedded
- Robust prediction interval estimation for Gaussian processes by cross-validation method
- Multineuron spike train analysis with R-convolution linear combination kernel
- Gaussian field on the symmetric group: prediction and learning
- Surrogate model approach for investigating the stability of a friction-induced oscillator of Duffing's type
- Sequential approximate optimization for design under uncertainty problems utilizing Kriging metamodeling in augmented input space
- Cross-validation estimation of covariance parameters under fixed-domain asymptotics
- Asymptotic analysis of the role of spatial sampling for covariance parameter estimation of Gaussian processes
- Streaming-Data Selection for Gaussian-Process Modelling
- Particle swarm optimization for adaptive hyper-parameters acquisition of Gaussian process regression
- A statistical framework to infer delay and direction of information flow from measurements of complex systems
- Fast Generalized Cross-Validation Algorithm for Sparse Model Learning
- A set‐based approach for hierarchical optimization problem using Bayesian active learning
- Gradient and uncertainty enhanced sequential sampling for global fit
- Dynamic characteristics and reliability analysis of parallel mechanism with clearance joints and parameter uncertainties
- Parameter Selection in Gaussian Process Interpolation: An Empirical Study of Selection Criteria
- Comparing scale parameter estimators for Gaussian process interpolation with the Brownian motion prior: leave-one-out cross validation and maximum likelihood
- Continuous-time linear time-varying system identification with a frequency-domain kernel-based estimator
- Efficient multiobjective optimization employing Gaussian processes, spectral sampling and a genetic algorithm
- Lengthscale-informed sparse grids for kernel methods in high dimensions
- Parallel cross-validation: a scalable fitting method for Gaussian process models
This page was built for publication: Predictive approaches for choosing hyperparameters in Gaussian processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2747213)
