系统梳理状态空间模型在长序列任务中的高效性与有效性。
Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models
- 分三类介绍SSM：基础型、结构化S4、选择性Mamba
- 相比Transformer，在长序列任务中性能相当但效率更高
- 适合想了解SSM理论基础的算法研究者
状态空间模型（SSMs）作为Transformer的有潜力替代方案，正受到越来越多关注。相较于Transformer，SSMs在处理序列数据或长上下文任务时表现更优，既能保持相近性能，又带来显著效率提升。本文系统综述了SSMs的理论基础、数学形式、与其他模型类别的对比及其广泛应用。我们将SSM系列分为三大类：原始SSM、以S4为代表的结构化SSM，以及以Mamba为代表的选择性SSM。重点剖析提升其有效性和效率的关键技术。希望本综述能为研究者理解SSMs的理论根基提供入门指引。
原文摘要 · Abstract (English)
State Space Models (SSMs) have emerged as a promising alternative to the popular transformer-based models and have been increasingly gaining attention. Compared to transformers, SSMs excel at tasks with sequential data or longer contexts, demonstrating comparable performances with significant efficiency gains. In this survey, we provide a coherent and systematic overview for SSMs, including their theoretical motivations, mathematical formulations, comparison with existing model classes, and various applications. We divide the SSM series into three main sections, providing a detailed introduction to the original SSM, the structured SSM represented by S4, and the selective SSM typified by Mamba. We put an emphasis on technicality, and highlight the various key techniques introduced to address the effectiveness and efficiency of SSMs. We hope this manuscript serves as an introduction for researchers to explore the theoretical foundations of SSMs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。