Evaluating Time Series Foundation Models on Noisy Periodic Time Series
While recent advancements in foundation models have significantly impacted machine learning, rigorous tests on the performance of time series foundation models (TSFMs) remain largely underexplored. This paper presents an empirical study evaluating the zero-shot, long-horizon forecasting abilities of several leading TSFMs over two synthetic datasets constituting noisy periodic time series. We assess model efficacy across different noise levels, underlying frequencies, and sampling rates. As benchmarks for comparison, we choose two statistical techniques: a Fourier transform (FFT)-based approach and a linear autoregressive (AR) model. Our findings demonstrate that while for time series with bounded periods and higher sampling rates, TSFMs can match or outperform the statistical approaches, their forecasting abilities deteriorate with longer periods, higher noise levels, lower sampling rates and more complex shapes of the time series.
Code (0)
등록된 구현이 없습니다.
Tasks
Time SeriesSimilar Papers 제목 키워드 기반
An Unsupervised Approach for Periodic Source Detection in Time Series
Detection of periodic patterns of interest within noisy time series data plays a critical role in various tasks, spanning from health monitoring to behavior analysis. Existing learning techniques often rely on labels or …
Self-Supervised LearningTime SeriesLeveraging Exogenous Signals for Hydrology Time Series Forecasting
Recent advances in time series research facilitate the development of foundation models. While many state-of-the-art time series foundation models have been introduced, few studies examine their effectiveness in specific…
Time Series ForecastingMPPN: Multi-Resolution Periodic Pattern Network For Long-Term Time Series Forecasting
Long-term time series forecasting plays an important role in various real-world scenarios. Recent deep learning methods for long-term series forecasting tend to capture the intricate patterns of time series by decomposit…
Time SeriesTime Series ForecastingA fully automated periodicity detection in time series
This paper presents a method to autonomously find periodicities in a signal. It is based on the same idea of using Fourier Transform and autocorrelation function presented in Vlachos et al. 2005. While showing interestin…
ClusteringTime SeriesTime Series AnalysisA spectral audit framework reveals task-dependent aperiodic reliance across EEG and ECG deep learning
Deep learning on physiological time series is interpreted through domain-specific features -- oscillatory rhythms in EEG, morphological complexes in ECG -- yet these signals sit atop a broadband aperiodic 1/f-like envelo…