DPSO augments standard PSO velocity updates with a KL-divergence-gated repulsion mechanism that improves performance 2-8x on multimodal benchmarks like Ackley and Levy while adding one hyperparameter and 15-25% runtime overhead.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Divergence-Guided Particle Swarm Optimization
DPSO augments standard PSO velocity updates with a KL-divergence-gated repulsion mechanism that improves performance 2-8x on multimodal benchmarks like Ackley and Levy while adding one hyperparameter and 15-25% runtime overhead.