PRISM：基于景观诊断的置换优化预测协议
PRISM: A Predictive Protocol for Permutation Optimization via Landscape Diagnostics
浏览论文内容
中文总结 AI 辅助
PRISM是基于景观诊断的置换优化预测协议，可在优化前预测搜索行为，适用于多类场景，能确定置换搜索的适用性及对应方案。
中文摘要 AI 辅助
当系统组件固定但其排序会影响性能时，就会出现置换优化问题。我们提出PRISM，一种用于置换优化的预测协议，该协议在选择搜索策略前会先测量适应度景观。PRISM采用低成本的景观诊断方法，包括单步移动自相关和适应度-距离相关性，以预测有用的变异算子、识别结构化搜索可能优于随机采样的情况，并检测搜索几乎无优势的区域。在合成置换景观、神经架构基准、科学机器学习流水线以及大语言模型指令排序等场景中，该协议在优化开始前就能对搜索行为做出可验证的预测。详尽的指令排序实验揭示了仅由置换引起的显著性能差异，而跨模型实验表明，有用的排序结构可在不同模型家族和任务难度间迁移。额外实验证明，在提示措辞优化后，指令排序仍具有重要影响，这表明内容优化与排序优化是互补的。研究结果表明，PRISM并非是一种通用的最优优化器，而是一种用于确定置换搜索何时有用、应采用何种表示与算子，以及何时更简单的替代方案更合适的框架。
英文摘要
Permutation optimization arises whenever the components of a system are fixed but their ordering affects performance. We introduce PRISM, a predictive protocol for permutation optimization that measures a fitness landscape before selecting a search strategy. PRISM uses inexpensive landscape diagnostics, including one-step move autocorrelation and fitness-distance correlation, to predict useful mutation operators, identify when structured search is likely to outperform random sampling, and detect regimes in which search provides little advantage. Across synthetic permutation landscapes, neural architecture benchmarks, scientific machine learning pipelines, and large-language-model instruction ordering, the protocol makes testable predictions about search behavior before optimization begins. Exhaustive instruction-ordering experiments reveal substantial performance variation induced solely by permutation, while cross-model experiments show that useful ordering structure can transfer across model families and task difficulty. Additional experiments demonstrate that instruction ordering remains consequential after prompt wording is optimized, indicating that content optimization and ordering optimization are complementary. The results position PRISM not as a universally superior optimizer, but as a framework for determining when permutation search is useful, which representation and operator should be used, and when simpler alternatives are preferable.
发表机构
- ML Collective（机器学习集体）
机构由 AI 辅助整理，请以论文原文为准。
