Particle Swarm Optimization (PSO) is a popular gradient-free meta-heuristic, but its many variants pose significant selection and tuning challenges for non-specialists. We introduce Automated Deep-learning-based Particle Swarm Optimization (AD-PSO), a framework that highly automates PSO configuration and execution. AD-PSO features a modular design, incorporating diverse PSO variants as interchangeable components. The core methodology involves training a hard-constrained Conditional Variational Autoencoder (CVAE) to map problem landscape features—obtained via Latin Hypercube Sampling (LHS)—to a near-optimal PSO configuration. This mapping is established a priori through meta-optimization. The user only specifies the maximum number of evaluations; AD-PSO then autonomously samples the function, computes its features, and uses the trained CVAE to generate and execute a tailored configuration. Experimental results demonstrate AD-PSO's strong adaptability. In 297 comparisons on the CEC2022 benchmark against 9 state-of-the-art competitors, AD-PSO won or tied in 239 cases (an 80.5% win/draw rate).
Yutong Zou, Peter J. Bentley· Annual Conference on Genetic...· 0 citations
Many Particle Swarm Optimization (PSO) variants often fail to approach the global optimum due to complex fitness landscapes and/or the structural rigidity of these variants. We developed a novel framework named PSO-SEM, centered on macro-evolutionary population management. PSO-SEM introduces three landscape-driven operators: Split (Topological Fission), Extinction (Density-driven Recycling), and Migration (Knowledge Transfer). These operators autonomously regulate the lifecycle of sub-swarms to intensify search in high-potential areas by identifying promising basins and recycling computational resources from stagnant regions. Experimental results show that PSO-SEM achieves a top-tier ranking and demonstrates significant competitiveness against 14 state-of-the-art algorithms. Behavioral monitoring and ablation studies confirm PSO-SEM's ability to maintain autonomous exploration/exploitation balance through landscape-based computational resource re-allocation. Our findings verify that PSO-SEM is an interpretable architecture that meets the diverse requirements of black-box optimization.