Building Trust in Black-box Optimization: A Comprehensive Framework for Explainability

TL;DR

This paper introduces a comprehensive, model-agnostic set of explainability metrics for surrogate optimization to improve transparency, trust, and interpretability in black-box function optimization, especially in batch evaluation settings.

Contribution

It proposes IEMSO, a novel framework of explainability metrics that provide both intermediate and post-hoc insights into surrogate optimization processes.

Findings

Metrics improve interpretability of surrogate models

Enhanced trust in optimization decisions

Effective across various benchmark problems

Abstract

Optimizing costly black-box functions within a constrained evaluation budget presents significant challenges in many real-world applications. Surrogate Optimization (SO) is a common resolution, yet its proprietary nature introduced by the complexity of surrogate models and the sampling core (e.g., acquisition functions) often leads to a lack of explainability and transparency. While existing literature has primarily concentrated on enhancing convergence to global optima, the practical interpretation of newly proposed strategies remains underexplored, especially in batch evaluation settings. In this paper, we propose \emph{Inclusive} Explainability Metrics for Surrogate Optimization (IEMSO), a comprehensive set of model-agnostic metrics designed to enhance the transparency, trustworthiness, and explainability of the SO approaches. Through these metrics, we provide both intermediate and post-hoc explanations to practitioners before and after performing expensive evaluations to gain trust. We consider four primary categories of metrics, each targeting a specific aspect of the SO process: Sampling Core Metrics, Batch Properties Metrics, Optimization Process Metrics, and Feature Importance. Our experimental evaluations demonstrate the significant potential of the proposed metrics across different benchmarks.