Projection predictive model selection for Gaussian processes

We propose a new method for simplification of Gaussian process (GP) models by projecting the information contained in the full encompassing model and selecting a reduced number of variables based on their predictive relevance. Our results on synthetic and real world datasets show that the proposed method improves the assessment of variable relevance compared to the automatic relevance determination (ARD) via the length-scale parameters. We expect the method to be useful for improving explainability of the models, reducing the future measurement costs and reducing the computation time for making new predictions.

• Publication year

  2015

• Venue

  International Workshop on Machine Learning for Signal Processing

• Publication date

  2015-10-16

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1109/MLSP.2016.7738829arXiv 1510.04813
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Comparison of Bayesian predictive methods for model selection

  2015influential reference
• Decoupling Shrinkage and Selection in Bayesian Linear Models: A Posterior Summary Perspective

  2014cited by this paper
• Industrial PLS model variable selection using moving window variable importance in projection

  2014cited by this paper
• Hierarchical Bayesian Survival Analysis and Projective Covariate Selection in Cardiovascular Event Risk Prediction

  2014cited by this paper
• A survey of Bayesian predictive methods for model assessment, selection and comparison

  2012cited by this paper
• Variable Selection for Nonparametric Gaussian Process Priors: Models and Computational Strategies.

  2011cited by this paper
• The predictive Lasso

  2010cited by this paper
• Variable Selection for Gaussian Process Models in Computer Experiments

  2006cited by this paper
• Computational approaches to motor learning by imitation.

  2003cited by this paper
• Variable selection in qualitative models via an entropic explanatory power

  2003cited by this paper
• Gene selection: a Bayesian variable selection approach

  2003cited by this paper
• Bayesian model assessment and selection using expected utilities

  2001influential reference
• Expectation Propagation for approximate Bayesian inference

  2001cited by this paper
• Model choice in generalised linear models: A Bayesian approach via Kullback-Leibler projections

  1998cited by this paper
• In Advances in Neural Information Processing Systems

  1996cited by this paper
• Regression Shrinkage and Selection via the Lasso

  1996cited by this paper
• BAYESIAN NON-LINEAR MODELING FOR THE PREDICTION COMPETITION

  1996cited by this paper
• Bayesian learning for neural networks

  1995cited by this paper
• Multivariate adaptive regression splines

  1990cited by this paper
• Bayesian Variable Selection in Linear Regression

  1988cited by this paper
• Bioinformatics Original Paper Bayesian Variable Selection for the Analysis of Microarray Data with Censored Outcomes

  year unknowncited by this paper
• Computational Statistics and Data Analysis Bayesian Projection Approaches to Variable Selection in Generalized Linear Models

  year unknowncited by this paper

• Kernel-Based Sparse Additive Nonlinear Model Structure Detection through a Linearization Approach

  2025cites this paper
• Urban heat exacerbates climatic risks to urban biodiversity

  2025cites this paper
• Improving the Quasi‐Biennial Oscillation via a Surrogate‐Accelerated Multi‐Objective Optimization

  2025cites this paper
• Interpret Gaussian Process Models by Using Integrated Gradients

  2024cites this paper
• A Gaussian process embedded feature selection method based on automatic relevance determination

  2024cites this paper
• A simple approach for local and global variable importance in nonlinear regression models

  2023cites this paper
• Bayesian Inference for Misspecified Generative Models

  2023cites this paper
• Advances in Projection Predictive Inference

  2023cites this paper
• Feature Collapsing for Gaussian Process Variable Ranking

  2022cites this paper
• Bayesian order identification of ARMA models with projection predictive inference

  2022influential citation
• Automatic Dynamic Relevance Determination for Gaussian process regression with high-dimensional functional inputs

  2022influential citation
• Machine learning-based analysis of overall stability constants of metal–ligand complexes

  2022cites this paper
• Perspectives on the integration between first-principles and data-driven modeling

  2022cites this paper
• Agile Project Management Based on Data Analysis for Information Management Systems

  2021cites this paper
• Latent space projection predictive inference

  2021cites this paper
• ZIARNISTA REPREZENTACJA POTENCJAŁU INFORMACYJNEGO ZMIENNYCH – PRZYKŁAD ZASTOSOWANIA

  2021cites this paper
• Study on the Location of Energy Meter Distribution Center based on Immune Algorithm

  2021cites this paper
• A new hybrid model to foretell thermal power efficiency from energy performance certificates at residential dwellings applying a Gaussian process regression

  2020cites this paper
• A new predictive model for the outlet turbidity in micro-irrigation sand filters fed with effluents using Gaussian process regression

  2020cites this paper
• Supplementary Material for “A Statistical Pipeline for Identifying Physical Features that Differentiate Classes of 3D Shapes”

  2020cites this paper
• Using reference models in variable selection

  2020cites this paper
• Prediction of outlet dissolved oxygen in micro-irrigation sand media filters using a Gaussian process regression

  2020cites this paper
• Bayesian Variable Selection

  2020cites this paper
• Variable selection for Gaussian process regression through a sparse projection

  2020influential citation
• Projection Predictive Inference for Generalized Linear and Additive Multilevel Models

  2020influential citation
• Data Analysis of Readiness Programs of Machine-Building Enterprises

  2020cites this paper
• A New Predictive Model for Evaluating Chlorophyll-a Concentration in Tanes Reservoir by Using a Gaussian Process Regression

  2020cites this paper
• Model Interpretation Through Lower-Dimensional Posterior Summarization

  2019cites this paper
• Gaussian Process Models of Sound Change in Indo-Aryan Dialectology

  2019cites this paper
• Monotone function estimation in the presence of extreme data coarsening: Analysis of preeclampsia and birth weight in urban Uganda

  2019cites this paper
• Assessment of predictive relevance of covariates in Gaussian process models

  2018cites this paper
• Projective Inference in High-dimensional Problems: Prediction and Feature Selection

  2018cites this paper
• Three Essays on Shrinkage Estimation and Model Selection of Linear and Nonlinear Time Series Models

  2018influential citation
• Predictor Variable Prioritization in Nonlinear Models: A Genetic Association Case Study

  2018cites this paper
• Local Interpretable Model-agnostic Explanations of Bayesian Predictive Models via Kullback-Leibler Projections

  2018cites this paper
• VARIABLE PRIORITIZATION IN NONLINEAR BLACK BOX METHODS: A GENETIC ASSOCIATION CASE STUDY1.

  2018cites this paper
• Model selection for Gaussian processes utilizing sensitivity of posterior predictive distribution

  2017cites this paper
• Using Stacking to Average Bayesian Predictive Distributions (with Discussion)

  2017cites this paper
• Variable selection for Gaussian processes via sensitivity analysis of the posterior predictive distribution

  2017cites this paper
• Gaussian process based approaches for survival analysis

  2016cites this paper
• Successful Machine Learning Strategies in an Environment of Intermittent Data Availability

  2016cites this paper
• Computational Statistics and Data Analysis

  year unknowncites this paper