效能與效率技術：狀態空間模型綜述

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

狀態空間模型（SSMs）已成為基於Transformer的流行模型的有力替代方案，並日益受到關注。與Transformer相比，SSMs在處理序列數據或較長上下文任務時表現出色，展現出可媲美的性能，同時顯著提升了效率。在本篇綜述中，我們為SSMs提供了一個連貫且系統的概述，涵蓋其理論動機、數學公式、與現有模型類別的比較，以及多種應用。我們將SSM系列劃分為三個主要部分，詳細介紹了原始SSM、以S4為代表的結構化SSM，以及以Mamba為例的選擇性SSM。我們著重於技術性，並強調了為提升SSMs有效性和效率而引入的各種關鍵技術。我們希望這份手稿能作為研究人員探索SSMs理論基礎的入門指南。

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.