This paper introduces an operator-selection factorization to analyze the proposal geometry of the Self-Organizing Migrating Algorithm (SOMA) and Differential Evolution (DE). The research demonstrates that the canonical SOMA proposal is affine in the search space and linear in an augmented state, providing interpretations of interpolation, projection, and masking. For DE/rand/1/bin, the paper derives finite-population moments and characterizes covariance and coordinate dependence. Experiments on the BBOB benchmark show that geometry-controlled and rotation-aware SOMA variants improve upon canonical SOMA and are competitive with established DE methods. AI
IMPACT Provides new analytical tools for understanding and designing population-based optimization algorithms.
RANK_REASON The cluster contains an academic paper detailing novel analytical methods and experimental results for swarm and evolutionary algorithms.
Read on arXiv cs.NE (Neural & Evolutionary) →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
