Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models
It serves as an introduction for researchers to explore SSMs, addressing the need for efficient models in sequential data tasks, but it is incremental as a survey paper.
This survey provides a systematic overview of State Space Models (SSMs), highlighting their emergence as an efficient alternative to transformers for sequential data and longer contexts, with comparable performance and significant efficiency gains.
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.