Open AccessPosted Content
Model selection for Gaussian processes utilizing sensitivity of posterior predictive distribution
Topi Paananen,Juho Piironen,Michael Riis Andersen,Aki Vehtari +3 more
- 21 Dec 2017
TL;DR: Two novel methods for simplifying Gaussian process (GP) models by examining the predictions of a full model in the vicinity of the training points and thereby ordering the covariates based on their predictive relevance are proposed.
read more
Abstract: We propose two novel methods for simplifying Gaussian process (GP) models by examining the predictions of a full model in the vicinity of the training points and thereby ordering the covariates based on their predictive relevance. Our results on synthetic and real world data sets demonstrate improved variable selection compared to automatic relevance determination (ARD) in terms of consistency and predictive performance. We expect our proposed methods to be useful in interpreting and understanding complex Gaussian process models.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Posted Content
Efficient estimation of divergence-based sensitivity indices with Gaussian process surrogates
Anne Eggels,Daan Crommelin +1 more
TL;DR: This work proposes to use Gaussian process (GP) surrogates to increase the number of samples in the combined input-output space, and investigates two estimators: one in which only the GP mean is used, and one which also accounts for the GP prediction variance.
2
Assessment of predictive relevance of covariates in Gaussian process models
Topi Paananen
- 13 Mar 2018
TL;DR: Two novel covariate selection methods for Gaussian process models are introduced and shown to be more consistent and produce submodels with a better predictive performance.
References
•Book
Bayesian learning for neural networks
Geoffrey E. Hinton,Radford M. Neal +1 more
- 01 Jan 1995
TL;DR: Bayesian Learning for Neural Networks shows that Bayesian methods allow complex neural network models to be used without fear of the "overfitting" that can occur with traditional neural network learning methods.
4.8K
Gaussian processes for machine learning
Carl E. Rasmussen,Christopher K. I. Williams +1 more
- 23 Nov 2005
TL;DR: The book provides a long-needed, systematic and unified treatment of theoretical and practical aspects of GPs in machine learning, targeted at researchers and students in machine learning and applied statistics.
4.6K
•Proceedings Article
Gaussian Processes for Regression
Christopher Williams,Carl Edward Rasmussen +1 more
- 27 Nov 1995
TL;DR: This paper investigates the use of Gaussian process priors over functions, which permit the predictive Bayesian analysis for fixed values of hyperparameters to be carried out exactly using matrix operations.
Hybrid Monte Carlo
TL;DR: In this article, a hybrid (molecular dynamics/Langevin) algorithm is used to guide a Monte Carlo simulation of lattice field theory, which is especially efficient for quantum chromodynamics which contain fermionic degrees of freedom.
4K
Updating the inverse of a matrix
TL;DR: The history of these fomulas is presented and various applications to statistics, networks, structural analysis, asymptotic analysis, optimization, and partial differential equations are discussed.
1.2K