Projection predictive model selection for Gaussian processes

Abstract

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.

A few minor changes in text

References in corpus (3)

• Expectation Propagation for approximate Bayesian inference
• Comparison of Bayesian predictive methods for model selection
• Variable Selection for Nonparametric Gaussian Process Priors: Models and Computational Strategies

Cited by in corpus (7)

• Projective Inference in High-dimensional Problems: Prediction and Feature Selection
• Model interpretation through lower-dimensional posterior summarization
• Local Interpretable Model-agnostic Explanations of Bayesian Predictive Models via Kullback-Leibler Projections
• Projection Predictive Inference for Generalized Linear and Additive Multilevel Models
• Latent space projection predictive inference
• Monotone function estimation in the presence of extreme data coarsening: Analysis of preeclampsia and birth weight in urban Uganda
• Variable selection for Gaussian process regression through a sparse projection