iBOA: The Incremental Bayesian Optimization Algorithm

TL;DR

The paper introduces iBOA, an incremental Bayesian optimization algorithm that learns and updates Bayesian networks without a population, enabling scalable and reliable optimization of complex problems.

Contribution

It presents a novel incremental approach to Bayesian optimization that updates network structure and parameters without relying on a solution population.

Findings

iBOA can learn unrestricted Bayesian networks incrementally

It effectively solves difficult nearly decomposable problems

Demonstrates scalability and reliability in optimization tasks

Abstract

This paper proposes the incremental Bayesian optimization algorithm (iBOA), which modifies standard BOA by removing the population of solutions and using incremental updates of the Bayesian network. iBOA is shown to be able to learn and exploit unrestricted Bayesian networks using incremental techniques for updating both the structure as well as the parameters of the probabilistic model. This represents an important step toward the design of competent incremental estimation of distribution algorithms that can solve difficult nearly decomposable problems scalably and reliably.