Unleashing the Potential of Differential Evolution through Individual-Level Strategy Diversity
- URL: http://arxiv.org/abs/2602.01147v1
- Date: Sun, 01 Feb 2026 10:45:44 GMT
- Title: Unleashing the Potential of Differential Evolution through Individual-Level Strategy Diversity
- Authors: Chenchen Feng, Minyang Chen, Zhuozhao Li, Ran Cheng,
- Abstract summary: We study the impact of individual-level strategy diversity on Differential Evolution's search dynamics and performance.<n>We introduce iStratDE, a minimalist variant that assigns mutation and crossover strategies independently to each individual.<n>Experiments on the CEC2022 benchmark suite and robotic control tasks demonstrate that iStratDE matches or surpasses established adaptive DE variants.
- Score: 6.921493684518839
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Since Differential Evolution (DE) is sensitive to strategy choice, most existing variants pursue performance through adaptive mechanisms or intricate designs. While these approaches focus on adjusting strategies over time, the structural benefits that static strategy diversity may bring remain largely unexplored. To bridge this gap, we study the impact of individual-level strategy diversity on DE's search dynamics and performance, and introduce iStratDE (DE with individual-level strategies), a minimalist variant that assigns mutation and crossover strategies independently to each individual at initialization and keeps them fixed throughout the evolutionary process. By injecting diversity at the individual level without adaptation or feedback, iStratDE cultivates persistent behavioral heterogeneity that is especially effective with large populations. Moreover, its communication-free construction possesses intrinsic concurrency, thereby enabling efficient parallel execution and straightforward scaling for GPU computing. We further provide a convergence analysis of iStratDE under standard reachability assumptions, which establishes the almost-sure convergence of the best-so-far fitness. Extensive experiments on the CEC2022 benchmark suite and robotic control tasks demonstrate that iStratDE matches or surpasses established adaptive DE variants. These results highlight individual-level strategy assignment as a straightforward yet effective mechanism for enhancing DE's performance. The source code of iStratDE is publicly accessible at: https://github.com/EMI-Group/istratde.
Related papers
- Strategy Executability in Mathematical Reasoning: Leveraging Human-Model Differences for Effective Guidance [86.46794021499511]
We show a previously underexplored gap between strategy usage and strategy executability.<n>We propose Selective Strategy Retrieval (SSR), a test-time framework that explicitly models executability.<n> SSR yields reliable and consistent improvements over direct solving, in-context learning, and single-source guidance.
arXiv Detail & Related papers (2026-02-26T03:34:23Z) - Integrating Diverse Assignment Strategies into DETRs [61.61489761918158]
Label assignment is a critical component in object detectors, particularly within DETR-style frameworks.<n>We propose LoRA-DETR, a flexible and lightweight framework that seamlessly integrates diverse assignment strategies into any DETR-style detector.
arXiv Detail & Related papers (2026-01-14T07:28:54Z) - Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents [90.45197506653341]
Large language model (LLM) agents increasingly rely on external tools such as search engines to solve complex, multi-step problems.<n>The trajectories of search agents are structurally heterogeneous, where variations in the number, placement, and outcomes of search calls lead to fundamentally different answer directions and reward distributions.<n>Standard policy gradient methods, which use a single global baseline, suffer from what we identify and formalize as cross-stratum bias.<n>We propose Stratified GRPO, whose central component, Stratified Advantage Normalization (SAN), partitions trajectories into homogeneous strata based on their structural properties and computes advantages locally within each
arXiv Detail & Related papers (2025-10-07T17:59:13Z) - Deep Reinforcement Learning-Assisted Component Auto-Configuration of Differential Evolution Algorithm for Constrained Optimization: A Foundation Model [12.957830806430733]
We introduce a novel framework for automated component configuration in Differential Evolution (DE) algorithm to address constrained optimization problems (COPs)<n>SuperDE is capable of recommending optimal per-generation configurations for unseen problems in a zero-shot manner.<n> Experimental results demonstrate that SuperDE significantly outperforms existing state-of-the-art algorithms on benchmark test suites.
arXiv Detail & Related papers (2025-09-14T00:14:40Z) - Evolutionary Policy Optimization [47.30139909878251]
On-policy reinforcement learning (RL) algorithms are widely used for their strong performance and training stability, but they struggle to scale with larger batch sizes.<n>We propose Evolutionary Policy Optimization (EPO), a hybrid that combines the scalability and diversity of EAs with the performance and stability of policy gradients.
arXiv Detail & Related papers (2025-03-24T18:08:54Z) - Evolution-based Region Adversarial Prompt Learning for Robustness Enhancement in Vision-Language Models [52.8949080772873]
We propose an evolution-based region adversarial prompt tuning method called ER-APT.<n>In each training iteration, we first generate AEs using traditional gradient-based methods.<n> Subsequently, a genetic evolution mechanism incorporating selection, mutation, and crossover is applied to optimize the AEs.<n>The final evolved AEs are used for prompt tuning, achieving region-based adversarial optimization instead of conventional single-point adversarial prompt tuning.
arXiv Detail & Related papers (2025-03-17T07:08:47Z) - An Efficient Reconstructed Differential Evolution Variant by Some of the Current State-of-the-art Strategies for Solving Single Objective Bound Constrained Problems [5.095287502726488]
We propose a strategy recombination and reconstruction differential evolution algorithm called reconstructed differential evolution (RDE) to solve single-objective bounded optimization problems.
Based on the benchmark suite of the 2024 IEEE Congress on Evolutionary Computation, we tested RDE and several other advanced differential evolution variants.
arXiv Detail & Related papers (2024-04-25T01:48:44Z) - Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution
Strategies [50.10277748405355]
Noise-Reuse Evolution Strategies (NRES) is a general class of unbiased online evolution strategies methods.
We show NRES results in faster convergence than existing AD and ES methods in terms of wall-clock time and number of steps across a variety of applications.
arXiv Detail & Related papers (2023-04-21T17:53:05Z) - Revisiting GANs by Best-Response Constraint: Perspective, Methodology,
and Application [49.66088514485446]
Best-Response Constraint (BRC) is a general learning framework to explicitly formulate the potential dependency of the generator on the discriminator.
We show that even with different motivations and formulations, a variety of existing GANs ALL can be uniformly improved by our flexible BRC methodology.
arXiv Detail & Related papers (2022-05-20T12:42:41Z) - Adaptive strategy in differential evolution via explicit exploitation
and exploration controls [0.0]
This paper proposes a new strategy adaptation method, named explicit adaptation scheme (Ea scheme)
Ea scheme separates multiple strategies and employs them on-demand.
Experimental studies on benchmark functions demonstrate the effectiveness of Ea scheme.
arXiv Detail & Related papers (2020-02-03T09:12:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.