测试深度时序模型能否超越记忆，发现部分模型具备隐式推理能力。
Implicit Reasoning in Deep Time Series Forecasting
- 设计分布外测试场景评估模型是否真懂时序规律。
- 线性、MLP和分块Transformer模型在新场景下表现良好。
- 为时序基础模型的智能本质提供初步证据，适合研究者参考。
近期，时序基础模型在多个领域的零样本时序预测中展现出令人瞩目的性能。然而，其成功是源于对时间动态的真实理解，还是仅靠记忆训练数据仍不明确。尽管语言模型中的隐式推理已被研究，但针对时序模型的类似评估尚未开展。本文首次尝试评估深度时序预测模型的推理能力。我们发现，某些线性、MLP-based及patch-based Transformer模型在系统性设计的分布外场景中仍能有效泛化，表明其可能具备超越简单模式记忆的隐式推理能力。
原文摘要 · Abstract (English)
Recently, time series foundation models have shown promising zero-shot forecasting performance on time series from a wide range of domains. However, it remains unclear whether their success stems from a true understanding of temporal dynamics or simply from memorizing the training data. While implicit reasoning in language models has been studied, similar evaluations for time series models have been largely unexplored. This work takes an initial step toward assessing the reasoning abilities of deep time series forecasting models. We find that certain linear, MLP-based, and patch-based Transformer models generalize effectively in systematically orchestrated out-of-distribution scenarios, suggesting underexplored reasoning capabilities beyond simple pattern memorization.
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。