# ms-Mamba: Multi-scale Mamba for Time-Series Forecasting

arXiv: https://arxiv.org/abs/2504.07654 · HTML: https://mlsanity.com/paper/2504.07654/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Time series forecasting with SSMs, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 40 of its 55 references that are in the map.
- First posted on arXiv 10 Apr 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Time series forecasting with SSMs](https://mlsanity.com/ssm/time-series-forecasting-with-ssms/)

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers](https://mlsanity.com/paper/2110.13985/) (2021)
- [Hungry Hungry Hippos: Towards Language Modeling with State Space Models](https://mlsanity.com/paper/2212.14052/) (2022)
- [Transformers in Time Series: A Survey](https://mlsanity.com/paper/2202.07125/) (2022)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https://mlsanity.com/paper/2106.09305/) (2021)
- [Long-term Forecasting with TiDE: Time-series Dense Encoder](https://mlsanity.com/paper/2304.08424/) (2023)
- [TSMixer: An All-MLP Architecture for Time Series Forecasting](https://mlsanity.com/paper/2303.06053/) (2023)
- [Frequency-domain MLPs are More Effective Learners in Time Series Forecasting](https://mlsanity.com/paper/2311.06184/) (2023)
- [Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures](https://mlsanity.com/paper/2207.01186/) (2022)
- [ETSformer: Exponential Smoothing Transformers for Time-series Forecasting](https://mlsanity.com/paper/2202.01381/) (2022)
- [Deep Learning for Time Series Forecasting: Tutorial and Literature Survey](https://mlsanity.com/paper/2004.10240/) (2020)
- [Is Mamba Effective for Time Series Forecasting?](https://mlsanity.com/paper/2403.11144/) (2024)
- [Hierarchical Multiscale Recurrent Neural Networks](https://mlsanity.com/paper/1609.01704/) (2016)

## Built on by (most cited first, 8 of 8)

- [GAMMA-Net: Adaptive Long-Horizon Traffic Spatio-Temporal Forecasting Model based on Interleaved Graph Attention and Multi-Axis Mamba](https://mlsanity.com/paper/2604.16859/) (2026)
- [ss-Mamba: Semantic-Spline Selective State-Space Model](https://mlsanity.com/paper/2506.14802/) (2025)
- [VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion](https://mlsanity.com/paper/2510.03244/) (2025)
- [ASGMamba: Adaptive Spectral Gating Mamba for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2602.01668/) (2026)
- [Permutation-Equivariant 2D State Space Models: Theory and Canonical Architecture for Multivariate Time Series](https://mlsanity.com/paper/2603.08753/) (2026)
- [PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shift](https://mlsanity.com/paper/2605.16351/) (2026)
- [A Unified Backbone--Expert Framework with Relation-Token and Residual--Classifier Interfaces for Automatic Modulation Recognition](https://mlsanity.com/paper/2608.15160/) (2026)
- [MARS: Multi-resolution Adaptive Routing for Sequential Recommendation](https://mlsanity.com/paper/2610.07505/) (2026)

## Abstract (arXiv)

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 (Deltas). 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. For example, on the Solar-Energy dataset, ms-Mamba outperforms its closest competitor S-Mamba (0.229 vs. 0.240 in terms of mean-squared error) while using fewer parameters (3.53M vs. 4.77M), less memory (13.46MB vs. 18.18MB), and less operations (14.93G vs. 20.53G MACs), averaged across four forecast lengths. Codes and models will be made available.