提出可自适应搜索时间序列配置的强化学习方法
TRACE-CASH: Trial-History-Conditioned Reinforcement Learning for Adaptive Configuration Exploration in Time-Series CASH
- 基于历史试验的分组强化学习，动态生成模型与超参组合
- 在41个数据集上平均排名领先，MASE和WQL指标最优
- 适合需要高效调参的时间序列预测场景
联合算法选择与超参数优化（CASH）在条件空间中搜索，所选模型决定哪些超参数有效。在时间序列预测中，时间选择、时序验证及高成本评估进一步增加复杂性。在统一的时间序列CASH（TS-CASH）评估协议下，现有对异构搜索方法的受控比较仍有限。本文研究TRACE-CASH，一种任务局部的混合顺序优化器，结合分组演员-评论家候选生成、固定规则的模型覆盖、验证引导的利用以及停滞后的探索策略。一个模型演员提出初始预测模型；三个模型条件演员生成时间、架构和训练动作；特定模型解码器构建最终评估的配置。我们在41个数据集-频率任务变体上，将TRACE-CASH与六种替代方法（随机、贝叶斯、进化、多目标、语言模型辅助搜索）进行对比。结果表明，TRACE-CASH在MASE和WQL两个指标上的平均排名最低；定性分析显示，在预定义的完整窗口和晚期窗口中，其窗口平均测试MASE排名也最低。这些结果支持了整个TRACE-CASH流程在所评估方法中具有竞争力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。