A Gaussian Process Regression Model for Distribution Inputs
From MaRDI portal
Abstract: Monge-Kantorovich distances, otherwise known as Wasserstein distances, have received a growing attention in statistics and machine learning as a powerful discrepancy measure for probability distributions. In this paper, we focus on forecasting a Gaussian process indexed by probability distributions. For this, we provide a family of positive definite kernels built using transportation based distances. We provide a probabilistic understanding of these kernels and characterize the corresponding stochastic processes. We prove that the Gaussian processes indexed by distributions corresponding to these kernels can be efficiently forecast, opening new perspectives in Gaussian process modeling.
Recommendations
- Gaussian process regression for maximum entropy distribution
- scientific article; zbMATH DE number 2226651
- Gaussian process regression with skewed errors
- Gaussian Process Regression Analysis for Functional Data
- Gaussian Process Functional Regression Modeling for Batch Data
- A Partially Linear Model Using a Gaussian Process Prior
- Gaussian process regression using partition resampling model
- Gaussian process regression and conditional polynomial chaos for parameter estimation
- On the inference of applying Gaussian process modeling to a deterministic function
- Generalized Gaussian process regression model for non-Gaussian functional data
Cited in
(21)- Multi-fidelity Gaussian process regression for prediction of random fields
- Bayesian regression and classification using Gaussian process priors indexed by probability density functions
- Asymptotic properties of the maximum likelihood and cross validation estimators for transformed Gaussian processes
- Gaussian processes with multidimensional distribution inputs via optimal transport and Hilbertian embedding
- Gaussian field on the symmetric group: prediction and learning
- A Partially Linear Model Using a Gaussian Process Prior
- scientific article; zbMATH DE number 125967 (Why is no real title available?)
- scientific article; zbMATH DE number 1329949 (Why is no real title available?)
- Multivariate Gaussian Random Fields over Generalized Product Spaces involving the Hypertorus
- Distribution regression model with a Reproducing Kernel Hilbert Space approach
- Wasserstein Regression
- On the use of Wasserstein distance in the distributional analysis of human decision making under uncertainty
- A scalable Matérn Gaussian process for learning spatial curves distributions
- Learning system parameters from Turing patterns
- Multivariate random fields evolving temporally over hyperbolic spaces
- Bayesian cluster analysis for registration and clustering homogeneous subgroups in multidimensional functional data
- Central limit theorems for general transportation costs
- Design and Analysis of Computer Experiments with both Numeral and Distributional Inputs
- Covariance parameter estimation of Gaussian processes with approximated functional inputs
- Error bounds for a kernel-based constrained optimal smoothing approximation
- Improved learning theory for kernel distribution regression with two-stage sampling
This page was built for publication: A Gaussian Process Regression Model for Distribution Inputs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4682941)
