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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
