mlsanityData to 14 Oct 2026

Time Series Forecasting Through the Lens of Dynamics

arXiv 2507.15774 ↗First posted 21 Jul 2025cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

While deep learning is facing an homogenization across modalities led by Transformers, they are still challenged by shallow linear models in the time series forecasting task. Our hypothesis is that models should learn a direct link from past to future data points, which we identify as a learning dynamics capability. We develop an original textttPRO-DYN nomenclature to analyze existing models through the lens of dynamics. Two observations thus emerge: 1. under-performing architectures learn dynamics at most partially, 2. the location of the dynamics block at the model end is of prime importance. Our systemic and empirical studies both confirm our observations on a set of performance-varying models with diverse backbones. We propose a simple plug-and-play methodology guiding model designs and improvements.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 38 of its 61 references that are in the map. First posted on arXiv 21 Jul 2025.

Builds on

38 of 61 references.

References · 38

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  4. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  5. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  6. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  7. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  8. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  9. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  10. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  11. 2024Chronos: Learning the Language of Time Seriescited by 759
  12. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
26 more
  1. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 607
  2. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 494
  3. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
  4. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 391
  5. 2022BEATs: Audio Pre-Training with Acoustic Tokenizerscited by 388
  6. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 332
  7. 2024TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methodscited by 249
  8. 2023FITS: Modeling Time Series with 10k Parameterscited by 195
  9. 2024Are Language Models Actually Useful for Time Series Forecasting?cited by 168
  10. 2016Long Short-Term Memory-Networks for Machine Readingcited by 161
  11. 2023FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspectivecited by 127
  12. 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 127
  13. 2023Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictorscited by 113
  14. 2023DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecastingcited by 109
  15. 2024Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecastingcited by 104
  16. 2025This Time is Different: An Observability Perspective on Time Series Foundation Modelscited by 68
  17. 2025TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecastingcited by 64
  18. 2023Effectively Modeling Time Series with Simple Discrete State Spacescited by 54
  19. 2024Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfercited by 32
  20. 2024Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspectivecited by 17
  21. 2023Mori-Zwanzig latent space Koopman closure for nonlinear autoencodercited by 12
  22. 2025Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Modelscited by 9
  23. 2024Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyondcited by 8
  24. 2025LETS Forecast: Learning Embedology for Time Series Forecastingcited by 6
  25. 2024EDformer: Embedded Decomposition Transformer for Interpretable Multivariate Time Series Predictionscited by 5
  26. 2024PSformer: Parameter-efficient Transformer with Segment Attention for Time Series Forecastingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Correct then Forecast: Observer State-Space Models for Time Series Forecastingcited by 0