Automated PSO Configuration Framework via Deep Neural Networks and Function Landscape Descriptors

Abstract

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).