A rank-conditioned α-stable perturbation for differential evolution: Separating perturbation frequency and tail heaviness
- 1Graduate School of Data Science, Chonnam National University, Gwangju, Republic of Korea
- 2Department of Lifelong Education, Kyungil University, Gyeongsangbuk-do, Republic of Korea
Abstract
Heavy-tailed perturbations are commonly used in differential evolution (DE) to restore diversity and mitigate premature convergence. Adaptive Cauchy perturbation refines this strategy by varying perturbation probabilities according to dimension-wise convergence, but it retains a fixed Cauchy law and cannot adjust perturbation severity across individuals. This paper proposes rank-conditioned α-stable perturbation, a two-level adaptive operator that decouples perturbation activation from tail-shape control. Dimension-wise convergence indicators determine coordinate-specific perturbation probabilities, while each individual’s fitness rank determines the stability index of a symmetric α-stable kernel. Thus, higher-ranked individuals receive lighter-tailed perturbations for local refinement, whereas lower-ranked individuals receive heavier-tailed perturbations for occasional long-range exploration. Unlike fixed-kernel heavy-tailed DE operators, the proposed operator induces a per-individual exploration–exploitation trade-off within each generation. It is embedded into L-SRTDE, the winner of the IEEE CEC 2024 competition, and evaluated on the IEEE CEC 2017 benchmark suite across multiple dimensions. Results show the best Friedman rankings among the compared methods and favorable Wilcoxon outcomes against recent DE variants. Controlled comparisons with conventional Cauchy and adaptive dimension-wise Cauchy perturbations show that rank-guided tail-shape adaptation complements probability-based activation, with modest overhead and stable performance across α-stable parameter settings.
Related
- AnnFlux: object-conditioned neural stochastic differential equations for single-cell perturbation dynamics
- GeoSinkhorn Flow: Geometry-Aware Flow Matching for Perturbation-Conditioned Dynamics in Single cell Data Phenoscapes
- Perturbation-based propagation of bacterial composition uncertainty improves robustness and reproducibility of microbiome differential abundance analysis.
- PerturbBridge: Conditional Latent Schr\"{o}dinger Bridge for Single-Cell Perturbation Prediction
- Why rescue-based transcript ranking can mislead: normalization displacement and shared-control coupling in perturbation transcriptomics
BibTeX
@article{choi2026rankconditioned,
title = {{A rank-conditioned α-stable perturbation for differential evolution: Separating perturbation frequency and tail heaviness}},
author = {Tae Jong Choi and Yeji An},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0357907},
url = {https://doi.org/10.1371/journal.pone.0357907},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A rank-conditioned α-stable perturbation for differential evolution: Separating perturbation frequency and tail heaviness
AU - Tae Jong Choi
AU - Yeji An
PY - 2026
DA - 2026/09/09
JO - PLOS One
DO - 10.1371/journal.pone.0357907
UR - https://doi.org/10.1371/journal.pone.0357907
AB - Heavy-tailed perturbations are commonly used in differential evolution (DE) to restore diversity and mitigate premature convergence. Adaptive Cauchy perturbation refines this strategy by varying perturbation probabilities according to dimension-wise convergence, but it retains a fixed Cauchy law and cannot adjust perturbation severity across individuals. This paper proposes rank-conditioned α-stable perturbation, a two-level adaptive operator that decouples perturbation activation from tail-shape control. Dimension-wise convergence indicators determine coordinate-specific perturbation probabilities, while each individual’s fitness rank determines the stability index of a symmetric α-stable kernel. Thus, higher-ranked individuals receive lighter-tailed perturbations for local refinement, whereas lower-ranked individuals receive heavier-tailed perturbations for occasional long-range exploration. Unlike fixed-kernel heavy-tailed DE operators, the proposed operator induces a per-individual exploration–exploitation trade-off within each generation. It is embedded into L-SRTDE, the winner of the IEEE CEC 2024 competition, and evaluated on the IEEE CEC 2017 benchmark suite across multiple dimensions. Results show the best Friedman rankings among the compared methods and favorable Wilcoxon outcomes against recent DE variants. Controlled comparisons with conventional Cauchy and adaptive dimension-wise Cauchy perturbations show that rank-guided tail-shape adaptation complements probability-based activation, with modest overhead and stable performance across α-stable parameter settings.
SN - 1932-6203
ER -