CriPS: Critical Dynamics in Particle Swarm Optimization
This is an incremental improvement for optimization algorithms in computational intelligence.
The authors tackled the problem of improving Particle Swarm Optimization by removing algorithm-induced scales to balance exploration and local search, resulting in a method that shows evidence for self-organized criticality and promising performance.
Particle Swarm Optimisation (PSO) makes use of a dynamical system for solving a search task. Instead of adding search biases in order to improve performance in certain problems, we aim to remove algorithm-induced scales by controlling the swarm with a mechanism that is scale-free except possibly for a suppression of scales beyond the system size. In this way a very promising performance is achieved due to the balance of large-scale exploration and local search. The resulting algorithm shows evidence for self-organised criticality, brought about via the intrinsic dynamics of the swarm as it interacts with the objective function, rather than being explicitly specified. The Critical Particle Swarm (CriPS) can be easily combined with many existing extensions such as chaotic exploration, additional force terms or non-trivial topologies.