SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention

Documenti analoghi

• Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
  di: Ilbert, Romain, et al.
  Pubblicazione: (2024)
• User-friendly Foundation Model Adapters for Multivariate Time Series Classification
  di: Feofanov, Vasilii, et al.
  Pubblicazione: (2024)
• Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias
  di: Odonnat, Ambroise, et al.
  Pubblicazione: (2023)
• Layer by layer, module by module: Choose both for optimal OOD probing of ViT
  di: Odonnat, Ambroise, et al.
  Pubblicazione: (2026)
• Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift
  di: Xie, Renchunzi, et al.
  Pubblicazione: (2024)