Bayesian Optimization Augmented with Actively Elicited Expert Knowledge

TL;DR

This paper presents a novel approach to incorporate expert knowledge into Bayesian optimization using a multi-task Siamese neural network architecture, significantly accelerating the optimization process even with biased expert input.

Contribution

The paper introduces a multi-task learning framework with Siamese networks for eliciting and transferring expert knowledge into Bayesian optimization, a novel integration not previously explored.

Findings

Significantly speeds up Bayesian optimization with expert knowledge.

Effective even when expert knowledge is biased.

Demonstrated on benchmark functions with simulated and real experts.

Abstract

Bayesian optimization (BO) is a well-established method to optimize black-box functions whose direct evaluations are costly. In this paper, we tackle the problem of incorporating expert knowledge into BO, with the goal of further accelerating the optimization, which has received very little attention so far. We design a multi-task learning architecture for this task, with the goal of jointly eliciting the expert knowledge and minimizing the objective function. In particular, this allows for the expert knowledge to be transferred into the BO task. We introduce a specific architecture based on Siamese neural networks to handle the knowledge elicitation from pairwise queries. Experiments on various benchmark functions with both simulated and actual human experts show that the proposed method significantly speeds up BO even when the expert knowledge is biased compared to the objective function.