Bayesian Experimental Design for Symbolic Discovery

ICIAM2023 Springer Series 2026 Open access

Read full text
Authors: Kenneth L. Clarkson, Cristina Cornelio, Sanjeeb Dash, J.P.M. Gonçalves, Lior Horesh, Nimrod Megiddo
DOI: 10.1007/978-981-95-1446-5_7
Cited by: 1
References: 7

Abstract

Abstract This study concerns the formulation and application of Bayesian optimal experimental design to symbolic discovery, which is the inference from observational data of predictive models taking general functional forms. We apply constrained first-order methods to optimize an appropriate selection criterion, using Hamiltonian Monte Carlo to sample from the prior. A step for computing the predictive distribution, involving convolution, is computed via either numerical integration, or via fast transform methods.

Fields of Study & Subjects

Optimal Experimental Design Methods Advanced Multi-Objective Optimization Algorithms Gaussian Processes and Bayesian Inference

Publication details

Journal / source
ICIAM2023 Springer Series
Publisher
Springer Nature Singapore
Pages
139–148
Publication date
1 January 2026
Language
EN