TRACE-CASH：面向时间序列CASH的试验历史条件强化学习自适应配置探索
TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH
AI总结：
本研究针对时间序列CASH的复杂搜索问题，提出TRACE-CASH方法，通过分组演员-评论家等技术优化配置探索，在41个任务变体上的MASE、WQL等指标表现最优，具备竞争力。
AI中文摘要：
组合算法选择与超参数优化（CASH）会在一个条件空间中进行搜索，所选模型决定了哪些超参数处于激活状态。在时间序列预测领域，时间选择、时序验证以及高成本评估进一步加剧了这一搜索的复杂度。目前，在统一的时间序列CASH（TS-CASH）评估协议下，对异构搜索方法开展的受控对比研究仍较为有限。在该背景下，我们研究了TRACE-CASH，这是一种任务局部混合序列优化器，它将分组演员-评论家候选生成与模型覆盖的固定规则、验证引导的利用机制以及进展停滞后的探索策略相结合。其中，模型演员会提出初始预测模型；三个模型条件演员分别生成时间、架构和训练相关的动作；一个特定模型的解码器则构建出最终待评估的配置。我们在41个数据集-频率任务变体上，将TRACE-CASH与六种不同类型的替代方法进行了对比，这些替代方法涵盖随机搜索、贝叶斯优化、进化算法、多目标优化以及语言模型辅助搜索。TRACE-CASH在MASE和WQL指标上均取得了最低的平均排名；此外，在预定义的完整窗口和后期窗口中，它的窗口平均测试MASE排名也最低。这些结果表明，完整的TRACE-CASH流程在被评估的方法中具备竞争力。
英文摘要：
Combined algorithm selection and hyperparameter optimization (CASH) searches a conditional space in which the selected model determines which hyperparameters are active. In time-series forecasting, temporal choices, chronological validation, and costly evaluations further complicate this search. Controlled comparisons of heterogeneous search methods under a shared time-series CASH (TS-CASH) evaluation protocol remain limited. Within this setting, we study TRACECASH, a task-local hybrid sequential optimizer combining grouped actor-critic candidate generation with fixed rules for model coverage, validation-guided exploitation, and exploration after stalled progress. A model actor proposes an initial forecasting model; three model-conditioned actors generate temporal, architectural, and training actions; and a modelspecific decoder constructs the configuration ultimately evaluated. We compare TRACE-CASH with six alternatives spanning random, Bayesian, evolutionary, multi-objective, and language-model-assisted search across 41 dataset-frequency task variants. TRACE-CASH has the lowest mean rank on both MASE and WQL. Descriptively, it also has the lowest window-averaged test-MASE rank in the predefined full and late windows. These results support the complete TRACECASH procedure as competitive among the evaluated methods.
