The problem of Time-series Forecasting is generally addressed by recurrent, Transformer-based and the recently proposed Mamba-based architectures. However, existing architectures generally process their input at a single temporal scale, which may be sub-optimal for many tasks where information changes over multiple time scales. In this paper, we introduce a novel architecture called Multi-scale Mamba (ms-Mamba) to address this gap. ms-Mamba incorporates multiple temporal scales by using multiple Mamba blocks with different sampling rates (s). Our experiments on many benchmarks demonstrate that ms-Mamba outperforms state-of-the-art approaches, including the recently proposed Transformer-based and Mamba-based models.
View on arXiv@article{karadag2025_2504.07654,
title={ ms-Mamba: Multi-scale Mamba for Time-Series Forecasting },
author={ Yusuf Meric Karadag and Sinan Kalkan and Ipek Gursel Dino },
journal={arXiv preprint arXiv:2504.07654},
year={ 2025 }
}