发表机构
Nanyang Technological University; Agency for Science, Technology and Research; Singapore Institute of Manufacturing Technology (SIMTech); Centre for Frontier AI Research, A*STAR（南洋理工大学; 新加坡科技研究局; 新加坡制造技术研究院; A*STAR前沿人工智能研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出ICG-MTO框架，利用冻结数值基础模型通过上下文学习推断引导信号，改进少样本多任务优化中的任务间耦合估计，在合成和真实问题上验证了有效性与通用性。
AI 中文摘要
多任务优化（MTO）同时处理一组优化任务，在有限的评估预算下，常常因任务间关系估计不准确而导致负迁移。本文提出上下文引导多任务优化（ICG-MTO），一种利用数值基础模型在少样本场景中改进任务间耦合估计的新框架。与传统仅依赖稀缺观测数据的方法不同，ICG-MTO采用冻结的基础模型，通过上下文学习推断辅助引导。该框架通过三个阶段运作：从已评估解构建算法特定的上下文查询，利用基础模型推断表征任务间预测关系的引导信号，并将该信号转化为算法特定的引导，用于最大后验耦合估计。该方法在优化早期数据稀缺阶段提供正则化，并随着任务特定观测的积累逐步放弃控制。我们将该框架实例化为多任务贝叶斯优化中的ICG-MTBO，使用方向性适应度类别查询来引导任务间耦合估计，并进一步在MFEA-II中实例化，使用决策空间重叠查询来引导随机交配概率估计。在合成基准和真实机器人臂控制问题上的实验，以及在不同采集函数和进化多任务下的评估，证明了ICG-MTO在少样本多任务优化中的有效性和通用性。
英文摘要
Multi-task optimization (MTO) addresses a set of optimization tasks simultaneously, often suffering from inaccurate inter-task relationship estimation under limited evaluation budgets, leading to negative transfer. This paper introduces In-Context Guidance Multitask Optimization (ICG-MTO), a novel framework that leverages numerical foundational models to improve inter-task coupling estimation in few-shot scenarios. Unlike conventional methods that rely solely on scarce observed data, ICG-MTO employs a frozen foundational model to infer auxiliary guidance through in-context learning. The framework operates through three stages: constructing an algorithm-specific in-context query from evaluated solutions, using the foundational model to infer a guidance signal characterizing predictive relationships among tasks, and translating this signal into algorithm-specific guidance for maximum-a-posteriori coupling estimation. This approach provides regularization during the early, data-scarce stages of optimization and gradually relinquishes control as task-specific observations accumulate. We instantiate the framework in multitask Bayesian optimization as ICG-MTBO, using directional fitness-class queries to guide inter-task coupling estimation, and further instantiate it in MFEA-II using decision-space-overlap queries to guide random mating probability estimation. Experiments across synthetic benchmarks and a real-world robot arm control problem, together with evaluations under different acquisition functions and evolutionary multitasking, demonstrate the effectiveness and generality of ICG-MTO for few-shot multitask optimization.
CommentsIn Submission to IEEE Transactions on Evolutionary Computation
