Why Attention Fails: The Degeneration of Transformers into MLPs in Time Series Forecasting

Documenti analoghi

• Why Do Transformers Fail to Forecast Time Series In-Context?
  di: Zhou, Yufa, et al.
  Pubblicazione: (2025)
• Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond
  di: Ke, Yekun, et al.
  Pubblicazione: (2024)
• Hyperparameter Tuning MLPs for Probabilistic Time Series Forecasting
  di: Madhusudhanan, Kiran, et al.
  Pubblicazione: (2024)
• Boosting MLPs with a Coarsening Strategy for Long-Term Time Series Forecasting
  di: Bian, Nannan, et al.
  Pubblicazione: (2024)
• MDMLP-EIA: Multi-domain Dynamic MLPs with Energy Invariant Attention for Time Series Forecasting
  di: Zhang, Hu, et al.
  Pubblicazione: (2025)