效能与效率技术：状态空间模型综述

Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models

March 14, 2025

作者: Xingtai Lv, Youbang Sun, Kaiyan Zhang, Shang Qu, Xuekai Zhu, Yuchen Fan, Yi Wu, Ermo Hua, Xinwei Long, Ning Ding, Bowen Zhou

cs.AI

摘要

状态空间模型（SSMs）作为一种有前景的替代方案，正逐渐受到关注，与流行的基于Transformer的模型形成对比。相较于Transformer，SSMs在处理序列数据或较长上下文任务时表现卓越，展现出可媲美的性能，同时显著提升了效率。本综述为SSMs提供了一个连贯且系统的概览，涵盖其理论动机、数学公式、与现有模型类别的比较，以及多样化的应用场景。我们将SSM系列划分为三大主要部分，分别详细介绍了原始SSM、以S4为代表的结构化SSM，以及以Mamba为典型的选择性SSM。我们着重于技术细节，强调了为提升SSMs有效性和效率而引入的各项关键技术。希望本综述能为研究人员探索SSMs的理论基础提供入门指导。

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.