@inproceedings{shihab-etal-2025-efficient,
    title = "Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments",
    author = "Shihab, Ibne Farabi  and
      Akter, Sanjeda  and
      Sharma, Anuj",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.emnlp-main.562/",
    doi = "10.18653/v1/2025.emnlp-main.562",
    pages = "11109--11137",
    ISBN = "979-8-89176-332-6",
    abstract = "As the deployment of AI models shifts towards edge devices, developing efficient sequence models has become critical. State-space models (SSMs), particularly Mamba, have emerged as strong rivals to Transformers due to their linear-time complexity and impressive performance across a range of tasks. However, their large parameter counts still hinder their use in resource-constrained environments. To address this, we propose a novel unstructured pruning framework specifically tailored for Mamba, achieving up to 70{\%} parameter reduction with only a 3{--}9{\%} drop in performance. Unlike pruning techniques designed for Transformers, our approach leverages Mamba{'}s unique recurrent dynamics by incorporating pruning based on both weight and gradient importance to preserve critical parameters, a gradual pruning schedule to maintain model stability, and a global strategy to optimize parameter allocation across the model. Extensive experiments on the WikiText-103, Long Range Arena, and ETT benchmarks demonstrate significant efficiency gains, including 1.77{\texttimes} faster inference and a 46{\%} reduction in memory usage. Our component analysis confirms Mamba{'}s robustness to pruning, highlighting the framework{'}s potential for enabling practical deployment while underscoring the need for careful evaluation to avoid introducing biases in sensitive applications."
}