发表机构
Sorbonne Université, CNRS, INRAE, IRD, iEES; LIP6, Sorbonne Université, CNRS; Jožef Stefan Institute（索邦大学、法国国家科学研究中心、法国农业食品环境研究院、法国发展研究所、环境与社会科学研究所; 巴黎第六大学信息处理实验室、索邦大学、法国国家科学研究中心; 约瑟夫·施特凡研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究黑盒优化中自动算法选择问题，提出基于多核聚类的无监督方法，通过多核k均值公式联合学习，在差分进化和粒子群优化任务中表现良好，能对核权重进行任务特定解释。
AI 中文摘要
黑盒优化中的自动算法选择通常依赖监督模型，将景观特征映射到算法性能标签。这类模型训练成本高、依赖基准测试且难以推广到未见过的问题类别。我们研究了一种无监督替代方法：对异构景观表示进行多核聚类。在聚类阶段不使用性能标签对问题实例进行分组，通过严格分开的三阶段评估协议将结果簇映射到求解器建议。我们采用多核k均值公式，在四个异构景观视图上联合学习簇分配和核权重。在固定评估预算下针对差分进化（DE）和粒子群优化（PSO）的仿射BBOB衍生选择器任务中，报告了50个独立随机种子的均值加减标准差选择器配置文件。多核聚类在DE组合上获得最强均值配置文件，在更紧凑的PSO组合上与领先基线竞争且名义上领先，在用于可视化的代表性中位数种子运行中，学习到的核权重保留了ELA和TransOptAS，同时将DeepELA和DoE2Vec的权重设为零，为选择器导向分组的多核模型保留哪些表示提供了特定任务的解释。
英文摘要
Automated algorithm selection in black-box optimization typically relies on supervised models that map landscape features to algorithm performance labels. Such models are costly to train, benchmark-dependent, and often fail to generalize to unseen problem classes. We study an unsupervised alternative: multi-kernel clustering over heterogeneous landscape representations, in which problem instances are grouped without using performance labels in the clustering stage, and the resulting clusters are mapped post hoc to solver recommendations through a strictly separated three-stage evaluation protocol. Drawing on two decades of advances in multiple kernel learning, we adopt a multi-kernel k-means formulation that jointly learns cluster assignments and kernel weights over four heterogeneous landscape views: ELA, DeepELA, DoE2Vec, and TransOptAS. On affine BBOB-derived selector tasks for Differential Evolution (DE) and Particle Swarm Optimization (PSO) at a fixed evaluation budget, we report mean plus or minus standard deviation selector profiles over 50 independent random seeds for stochastic configurations. Multi-kernel clustering obtains the strongest mean profile on the DE portfolio and remains competitive with, and nominally ahead of, the leading baselines on the more compressed PSO portfolio, where differences among the best methods are small relative to stochastic variation. In representative median-seed runs used for visualization, the learned kernel weights retain ELA and TransOptAS while assigning zero weight to DeepELA and DoE2Vec, providing a task-specific interpretation of which representations are retained by the multi-kernel model for selector-oriented grouping.
