发表机构
The Hong Kong Polytechnic University; China University of Petroleum (East China)（香港理工大学; 中国石油大学（华东））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对进化迁移优化（ETO）评估耗时问题，将任务参数化应用的串行计算重构为并行形式，在两类优化场景下分别实现256.72倍、93.91倍加速，为可扩展ETO提供实用方案并开源相关代码。
AI 中文摘要
随着进化迁移优化（ETO）扩展到更大规模的相关任务集合，问题评估可能成为运行时间增长的主要来源。本研究针对任务参数化应用中问题侧评估的扩展性展开研究，将特定应用的串行计算重新构造为适合并行执行的形式。我们将评估扩展性分为两个层面：被评估任务的数量，以及每个任务内部的工作负载。在多任务优化中，采用累积连杆方向的累积矩阵表示对矩阵递归机械臂评估进行重新构造；在序列迁移优化中，采用轨迹与碰撞计算的混合矩阵表示对逐点B样条轨迹评估进行重新构造。两种重新构造均与参考评估保持高度数值一致性，并大幅降低运行时间，分别实现了256.72倍和93.91倍的端到端加速。这些结果表明，问题侧重新构造是实现可扩展ETO的实用途径。所有应用实现与实验脚本均以开源形式发布，以支持可复现性与复用。
英文摘要
As evolutionary transfer optimization (ETO) scales to larger collections of related tasks, problem evaluation can become a major source of runtime growth. This work studies problem-side evaluation scaling in task-parameterized applications and reformulates application-specific serial computations into forms suitable for parallel execution. We organize evaluation scaling into two levels: the number of evaluated tasks and the workload within each task. In multi-task optimization, matrix-recursive kinematic-arm evaluation is reformulated using an accumulation-matrix representation of cumulative link directions. In sequential transfer optimization, pointwise B-spline trajectory evaluation is reformulated using a blending-matrix representation for trajectory and collision computations. Both reformulations maintain close numerical agreement with their reference evaluations and substantially reduce runtime, yielding $256.72\times$ and $93.91\times$ end-to-end speedups, respectively. These results demonstrate problem-side reformulation as a practical route toward scalable ETO. Both application implementations and experimental scripts are released as open source to support reproducibility and reuse.
CommentsAccepted at the 2026 International Conference on Machine Intelligence and Nature-Inspired Computing (MIND 2026)
