ms-Mamba: Multi-scale Mamba for Time-Series Forecasting
This addresses a gap in time-series forecasting for tasks where information changes over multiple scales, though it appears incremental as it builds on existing Mamba-based methods.
The paper tackles the problem of time-series forecasting by proposing a multi-scale Mamba architecture to process information across multiple temporal scales, and it demonstrates that ms-Mamba outperforms state-of-the-art models on benchmarks.
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 ($Δ$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.