On synthetic noisy periodic series, time-series foundation models match or beat FFT/AR baselines only for short, smooth, high-sample-rate signals, and degrade sharply when periods grow and sampling gets sparse.
Foundation models for time series analysis: A tutorial and survey,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Evaluating Time Series Foundation Models on Noisy Periodic Time Series
On synthetic noisy periodic series, time-series foundation models match or beat FFT/AR baselines only for short, smooth, high-sample-rate signals, and degrade sharply when periods grow and sampling gets sparse.