测试发现主流时序大模型在云数据上零样本预测表现差，连简单线性模型都比不过。
Performance of Zero-Shot Time Series Foundation Models on Cloud Data
- 用多个知名时序大模型测试云数据零样本预测效果
- 大模型普遍被简单线性基线超越，部分出现随机乱跳的异常输出
- 揭示时序大模型在云数据场景存在广泛失效问题，适合关注模型局限性的研究者
时序基础模型（FMs）作为零样本多领域预测的流行范式，通过在大量多样化数据集上训练，宣称可在包括云数据在内的多个时序领域有效预测。本文检验了这一说法，探究了FMs在云数据上的表现。实证结果表明，许多知名FMs在此设置下无法生成有意义或准确的零样本预测，其性能始终被简单线性基线模型超越。此外，我们还观察到若干有趣病理现象，例如某些情况下模型突然输出看似随机、不规则的预测。这些结果暗示时序基础模型在建模云数据方面存在普遍失败。
原文摘要 · Abstract (English)
Time series foundation models (FMs) have emerged as a popular paradigm for zero-shot multi-domain forecasting. FMs are trained on numerous diverse datasets and claim to be effective forecasters across multiple different time series domains, including cloud data. In this work we investigate this claim, exploring the effectiveness of FMs on cloud data. We demonstrate that many well-known FMs fail to generate meaningful or accurate zero-shot forecasts in this setting. We support this claim empirically, showing that FMs are outperformed consistently by simple linear baselines. We also illustrate a number of interesting pathologies, including instances where FMs suddenly output seemingly erratic, random-looking forecasts. Our results suggest a widespread failure of FMs to model cloud data.
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。