KnowraGaussian processLinked fromLinked fromThe 15 pages that link to Gaussian process, each with the reason it gives.All 15Broader topic 4Related 6Narrower topic 3Compared with 2Stochastic processBroader topic: It supports prediction over functions and spatially varying quantities.Normal distributionBroader topic: It extends normal modeling from scalar quantities to entire functions.Gaussian functionRelated: Gaussian functions often serve as covariance kernels in these function-valued models.Gaussian distributionBroader topic: It extends Gaussian uncertainty from a single quantity to entire functions.Large deviation theoryCompared with: Gaussian models describe common fluctuations, whereas large deviations can capture non-Gaussian tails.Positive-definite matrixRelated: Its kernel must generate positive-semidefinite Gram matrices for every finite set of inputs.Conjugate gradient methodRelated: Large-scale inference can use conjugate gradients to apply covariance inverses without explicitly computing them.Multivariate normal distributionNarrower topic: It extends the same joint-normal structure from finite vectors to functions.KrigingNarrower topic: Kriging predictions also arise as conditional means under Gaussian spatial models.Paul LévyCompared with: Brownian motion is Gaussian, while many Lévy processes allow non-Gaussian jumps.Kolmogorov extension theoremBroader topic: Consistent Gaussian finite-dimensional laws provide a common route to defining such processes.Bochner's theoremRelated: Positive-definite covariance functions define valid stationary Gaussian processes.Kolmogorov continuity theoremNarrower topic: Increment bounds provide a standard route to continuous versions of Gaussian processes.Woodbury matrix identityRelated: Low-rank covariance approximations use Woodbury to accelerate inference.Kosambi–Karhunen–Loève theoremRelated: Its eigenfunction expansion provides a basis for simulation and finite-dimensional approximation.
KnowraGaussian processLinked fromLinked fromThe 15 pages that link to Gaussian process, each with the reason it gives.All 15Broader topic 4Related 6Narrower topic 3Compared with 2Stochastic processBroader topic: It supports prediction over functions and spatially varying quantities.Normal distributionBroader topic: It extends normal modeling from scalar quantities to entire functions.Gaussian functionRelated: Gaussian functions often serve as covariance kernels in these function-valued models.Gaussian distributionBroader topic: It extends Gaussian uncertainty from a single quantity to entire functions.Large deviation theoryCompared with: Gaussian models describe common fluctuations, whereas large deviations can capture non-Gaussian tails.Positive-definite matrixRelated: Its kernel must generate positive-semidefinite Gram matrices for every finite set of inputs.Conjugate gradient methodRelated: Large-scale inference can use conjugate gradients to apply covariance inverses without explicitly computing them.Multivariate normal distributionNarrower topic: It extends the same joint-normal structure from finite vectors to functions.KrigingNarrower topic: Kriging predictions also arise as conditional means under Gaussian spatial models.Paul LévyCompared with: Brownian motion is Gaussian, while many Lévy processes allow non-Gaussian jumps.Kolmogorov extension theoremBroader topic: Consistent Gaussian finite-dimensional laws provide a common route to defining such processes.Bochner's theoremRelated: Positive-definite covariance functions define valid stationary Gaussian processes.Kolmogorov continuity theoremNarrower topic: Increment bounds provide a standard route to continuous versions of Gaussian processes.Woodbury matrix identityRelated: Low-rank covariance approximations use Woodbury to accelerate inference.Kosambi–Karhunen–Loève theoremRelated: Its eigenfunction expansion provides a basis for simulation and finite-dimensional approximation.