Preprint
Aug 2026
End-to-End Neural Decomposition with Koopman Operators for Time-Series Forecasting
This study proposes an end-to-end architecture that integrates a learnable signal decomposition module with both frequency-independent and frequency-dependent Koopman based networks for sequence forecasting and demonstrates that decomposing a signal into a frequency-independent trend component and a frequency-dependent...
De-Yan Lu, Xugang Lu, Yu Tsao et al.
· 0 citations