Research
MambaSL: Exploring Single-Layer Mamba for Time Series Classification
arXiv:2604.15174v1 Announce Type: new Abstract: Despite recent advances in state space models (SSMs) such as Mamba across various sequence domains, research on their standalone capacity for time serie
arXiv:2604.15174v1 Announce Type: new Abstract: Despite recent advances in state space models (SSMs) such as Mamba across various sequence domains, research on their standalone capacity for time series classification (TSC) has remained limited. We propose MambaSL, a framework that minimally redesigns the selective SSM and projection layers of a single-layer Mamba, guided by four TSC-specific hypotheses. To address benchmarking limitations -- restricted configurations, partial University of East Anglia (UEA) dataset coverage, and insufficiently reproducible setups -- we re-evaluate 20 strong baselines across all 30 UEA datasets under a unified protocol. As a result, MambaSL achieves state-of-the-art performance with statistically significant average improvements, while ensuring reproducibility via public checkpoints for all evaluated models. Together with visualizations, these results demonstrate the potential of Mamba-based architectures as a TSC backbone.
Related
- On the Expressive Power and Limitations of Multi-Layer SSMs
- COREY: A Prototype Study of Entropy-Guided Operator Fusion with Hadamard Reparameterization for Selective State Space Models
- Interventional Time Series Priors for Causal Foundation Models
- Time-Series Classification with Multivariate Statistical Dependence Features
- FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction
Source: arXiv cs.LG | 2026-04-17