Leonardo Ferreira Guilhoto and Paris Perdikaris have published a paper titled, “Composite Bayesian Optimization In Function Spaces Using NEON – Neural Epistemic Operator Networks” on April 3rd, 2024
The paper, published on arXiv, is titled, “Composite Bayesian Optimization In Function Spaces Using NEON – Neural Epistemic Operator Networks.”
Title
Composite Bayesian Optimization In Function Spaces Using NEON – Neural Epistemic Operator Networks
Abstract
Operator learning is a rising field of scientific computing where inputs or outputs of a machine learning model are functions defined in infinite-dimensional spaces. In this paper, we introduce NEON (Neural Epistemic Operator Networks), an architecture for generating predictions with uncertainty using a single operator network backbone, which presents orders of magnitude less trainable parameters than deep ensembles of comparable performance. We showcase the utility of this method for sequential decision-making by examining the problem of composite Bayesian Optimization (BO), where we aim to optimize a function f=g∘h, where h:X→C(Y,Rds) is an unknown map which outputs elements of a function space, and g:C(Y,Rds)→R is a known and cheap-to-compute functional. By comparing our approach to other state-of-the-art methods on toy and real world scenarios, we demonstrate that NEON achieves state-of-the-art performance while requiring orders of magnitude less trainable parameters.