 TimeMixer: Decomposable Multiscale Mixing for Time Series ForecastingInternational Conference on Learning Representations (ICLR), 2024 |
 Learning Gradients of Convex Functions with Monotone Gradient NetworksIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 |
 A Time Series is Worth 64 Words: Long-term Forecasting with TransformersInternational Conference on Learning Representations (ICLR), 2022 |
 Are Transformers Effective for Time Series Forecasting?AAAI Conference on Artificial Intelligence (AAAI), 2022 |
 Modern Koopman Theory for Dynamical SystemsSIAM Review (SIAM Rev.), 2021 |
 Attention Is All You NeedNeural Information Processing Systems (NeurIPS), 2017 |
