DesignX: Human-Competitive Algorithm Designer for Black-Box Optimization

TL;DR

DesignX is an automated framework that rapidly generates highly effective black-box optimizers tailored to specific problems, outperforming human-designed algorithms through reinforcement learning and modular design.

Contribution

The paper introduces the first automated algorithm design framework for black-box optimization, combining modular algorithm spaces with dual-agent reinforcement learning for rapid, high-quality optimizer generation.

Findings

DesignX-generated optimizers outperform human-crafted ones on various benchmarks.

The system discovers novel algorithm patterns beyond expert intuition.

Optimizers are generated within seconds and improve through autonomous learning.

Abstract

Designing effective black-box optimizers is hampered by limited problem-specific knowledge and manual control that spans months for almost every detail. In this paper, we present \textit{DesignX}, the first automated algorithm design framework that generates an effective optimizer specific to a given black-box optimization problem within seconds. Rooted in the first principles, we identify two key sub-tasks: 1) algorithm structure generation and 2) hyperparameter control. To enable systematic construction, a comprehensive modular algorithmic space is first built, embracing hundreds of algorithm components collected from decades of research. We then introduce a dual-agent reinforcement learning system that collaborates on structural and parametric design through a novel cooperative training objective, enabling large-scale meta-training across 10k diverse instances. Remarkably, through days of autonomous learning, the DesignX-generated optimizers continuously surpass human-crafted optimizers by orders of magnitude, either on synthetic testbed or on realistic optimization scenarios such as Protein-docking, AutoML and UAV path planning. Further in-depth analysis reveals DesignX's capability to discover non-trivial algorithm patterns beyond expert intuition, which, conversely, provides valuable design insights for the optimization community. We provide DesignX's Python project at~ https://github.com/MetaEvo/DesignX.