Variable selection for Gaussian processes via sensitivity analysis of the posterior predictive distribution

Abstract

Variable selection for Gaussian process models is often done using automatic relevance determination, which uses the inverse length-scale parameter of each input variable as a proxy for variable relevance. This implicitly determined relevance has several drawbacks that prevent the selection of optimal input variables in terms of predictive performance. To improve on this, we propose two novel variable selection methods for Gaussian process models that utilize the predictions of a full model in the vicinity of the training points and thereby rank the variables based on their predictive relevance. Our empirical results on synthetic and real world data sets demonstrate improved variable selection compared to automatic relevance determination in terms of variability and predictive performance.

Minor changes to text, additions to supplementary material

Cited by in corpus (7)

• Model Predictive Robustness of Signal Temporal Logic Predicates
• Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science Domains
• Computationally Efficient High-Dimensional Bayesian Optimization via Variable Selection
• Fast and Scalable Spike and Slab Variable Selection in High-Dimensional Gaussian Processes
• Variable selection for Gaussian process regression through a sparse projection
• Uncertainty-aware Sensitivity Analysis Using Rényi Divergences
• Efficient estimation of divergence-based sensitivity indices with Gaussian process surrogates