arXiv cs.AI· Sourish Gunesh Dhekane, Abinaya Kumar, Torsten Woertwein, Yan-Bo Lin, Thomas Ploetz, Shabnam Ghaffarzadegan·· 3 小时前AI 评分35
量化时间序列基础模型对传感器数据采样频率的不变性
Quantifying the Sampling Frequency Invariance of Time-Series Foundation Models for Sensor Data Applications
AI 导读
一项 arXiv 研究对 MOMENT、Chronos-2、Moirai-MoE 和 TimesFM 四个时间序列基础模型（TSFM）进行压力测试，量化其在采样频率变化下的不变性。研究提出 FSI、FDI、CDI 三项新指标，分别考察嵌入偏移、预测性能与下游性能的退化。结果表明采样频率不变性取决于信号原生采样频率与任务所需带宽之间的余量，并可视为“信号×模型”组合的可测量属性。
正文 · 原文
Abstract:Time-Series Foundation Models (TSFMs) are increasingly used in sensor applications, where sampling frequency (SF) varies across sensors, devices, and operating modes (e.g., power saving). Ideally, TSFMs must remain effective during such SF changes, provided the SF retains task-critical bandwidth. In this paper, we stress-test 4 prominent TSFMs: MOMENT, Chronos-2, Moirai-MoE, and TimesFM, to quantify their SF-invariance and investigate whether their behavior tracks the resulting loss of information bandwidth rather than the SF value itself. Our stress-test probes 3 dimensions: (i) the shift in embeddings, (ii) the degradation in forecasting performance, and (iii) the degradation in downstream performance, quantified by three novel metrics: FSI, FDI, and CDI, respectively. To our knowledge, this is the first study to place SF-invariance at the core of TSFM evaluations. Our results characterize: (i) how SF-invariance depends on the margin between signal's native-SF and the bandwidth its task requires, (ii) how much of that invariance the choice of TSFM explains, and (iii) how much of TSFM's performance degradation under a lower SF reflects information loss rather than a limitation of their abilities. These findings reframe SF-invariance as a measurable, signal-aware property of the (signal X TSFM) pair, and guide practitioners on when TSFMs display SF-invariance.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.14425 [cs.LG] |
| (or arXiv:2611.14425v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14425 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sourish Gunesh Dhekane [view email]
[v1]
Tue, 10 Nov 2026 18:01:23 UTC (1,969 KB)
来源：arXiv cs.AI · arxiv.org