A Constrained Learning-Based Competitive Swarm Optimizer for Large-Scale Multiobjective Optimization

View Full Paper

Ask AI

Bookmark

Authors

Discussion

The proposed CL-CSO improves convergence speed in large-scale multiobjective optimization, suggesting a new learning approach.

CL-CSO enhances convergence speed by addressing limitations of pairwise random competition, allowing more efficient learning.
In experiments, CL-CSO performed well on benchmark tests involving 2-3 objectives and 500-5000 decision variables.
The method includes reference vectors and intra-subregion learning strategies, improving learning effects of particles.
CL-CSO also applies a GM assisted evolutionary strategy to promote diversity and quality in solutions.

Li et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark