Rule-based Bayesian regression

DOI10.1007/S11222-022-10100-7zbMATH Open1490.62012arXiv2008.00422OpenAlexW3046754200MaRDI QIDQ2152549FDOQ2152549

Authors: Themistoklis Botsas, Lachlan R. Mason, Indranil Pan 

Publication date: 8 July 2022

Published in: Statistics and Computing (Search for Journal in Brave)

Abstract: We introduce a novel rule-based approach for handling regression problems. The new methodology carries elements from two frameworks: (i) it provides information about the uncertainty of the parameters of interest using Bayesian inference, and (ii) it allows the incorporation of expert knowledge through rule-based systems. The blending of those two different frameworks can be particularly beneficial for various domains (e.g. engineering), where, even though the significance of uncertainty quantification motivates a Bayesian approach, there is no simple way to incorporate researcher intuition into the model. We validate our models by applying them to synthetic applications: a simple linear regression problem and two more complex structures based on partial differential equations. Finally, we review the advantages of our methodology, which include the simplicity of the implementation, the uncertainty reduction due to the added information and, in some occasions, the derivation of better point predictions, and we address limitations, mainly from the computational complexity perspective, such as the difficulty in choosing an appropriate algorithm and the added computational burden.

Full work available at URL: https://arxiv.org/abs/2008.00422

Recommendations

• Constructing rule-based models using the belief functions framework
• On Bayesian estimation of regression models subject to uncertainty about functional constraints
• Remarks on kernel Bayes' rule
• Boolean regression
• scientific article; zbMATH DE number 426013

zbMATH Keywords

Bayesian inferenceGaussian processesB-splinesadvection-diffusionprobabilistic programming

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Bayesian inference (62F15)

Cites Work

• BART: Bayesian additive regression trees
• Title not available (Why is that?)
• Pattern recognition and machine learning.
• A Simplex Method for Function Minimization
• Monte Carlo sampling methods using Markov chains and their applications
• A practical guide to splines
• Advanced Lectures on Machine Learning
• Learning data-driven discretizations for partial differential equations
• Expert Knowledge Elicitation: Subjective but Scientific

Cited In (2)

• Bayes discriminant rules with ordered predictors
• Constructing rule-based models using the belief functions framework

Uses Software

• PyMC
• BayesDA
• RStan
• TensorFlow
• rstan
• GitHub
• BartPy
• PRMLT

This page was built for publication: Rule-based Bayesian regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2152549)