提出可适配任意基的状态空间模型，突破传统多项式限制。
SaFARi: State-Space Models for Frame-Agnostic Representation
- 用任意基构建状态空间模型，不再局限于多项式
- 统一了现有方法如HiPPO，扩展了模型多样性
- 适合研究长序列建模与基础架构设计的学者
状态空间模型（SSMs）近年成为在线函数逼近和长程依赖数据建模的强大工具。然而，此前仅探索过少数几种多项式基，最先进的实现也仅基于有限选项中的最优者。本文提出一种通用方法，可基于任意基或框架构建SSM，突破了传统多项式约束。该框架不仅涵盖已知的HiPPO方法，还支持无限多样的“物种”形式，构成全新的状态空间模型架构。我们称此方法为SaFARi：用于帧无关表示的状态空间模型。
原文摘要 · Abstract (English)
State-Space Models (SSMs) have re-emerged as a powerful tool for online function approximation, and as the backbone of machine learning models for long-range dependent data. However, to date, only a few polynomial bases have been explored for this purpose, and the state-of-the-art implementations were built upon the best of a few limited options. In this paper, we present a generalized method for building an SSM with any frame or basis, rather than being restricted to polynomials. This framework encompasses the approach known as HiPPO, but also permits an infinite diversity of other possible "species" within the SSM architecture. We dub this approach SaFARi: SSMs for Frame-Agnostic Representation.
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。