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

Romain Ilbert; Ambroise Odonnat; Vasilii Feofanov; Aladin Virmaux; Giuseppe Paolo; Themis Palpanas; Ievgen Redko

2024 ICML ICML 2024

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

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Data Science & Analytics

Authors

Romain Ilbert, Ambroise Odonnat, Vasilii Feofanov, Aladin Virmaux, Giuseppe Paolo, Themis Palpanas, Ievgen Redko

Topics

Machine Learning > Optimization & Theory > Optimization Deep Learning > Architectures > Transformers Data Science & Analytics > Methods > Time Series Analysis

Keywords

transformer sharpness-aware minimization multivariate time series long-term forecasting channel-wise attention samformer

Download PDF