Time-SSM: Simplifying and Unifying State Space Models for Time Series Forecasting

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hu, Jiaxi, Lan, Disen, Zhou, Ziyu, Wen, Qingsong, Liang, Yuxuan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929419251089408
author Hu, Jiaxi
Lan, Disen
Zhou, Ziyu
Wen, Qingsong
Liang, Yuxuan
author_facet Hu, Jiaxi
Lan, Disen
Zhou, Ziyu
Wen, Qingsong
Liang, Yuxuan
contents State Space Models (SSMs) have emerged as a potent tool in sequence modeling tasks in recent years. These models approximate continuous systems using a set of basis functions and discretize them to handle input data, making them well-suited for modeling time series data collected at specific frequencies from continuous systems. Despite its potential, the application of SSMs in time series forecasting remains underexplored, with most existing models treating SSMs as a black box for capturing temporal or channel dependencies. To address this gap, this paper proposes a novel theoretical framework termed Dynamic Spectral Operator, offering more intuitive and general guidance on applying SSMs to time series data. Building upon our theory, we introduce Time-SSM, a novel SSM-based foundation model with only one-seventh of the parameters compared to Mamba. Various experiments validate both our theoretical framework and the superior performance of Time-SSM.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16312
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Time-SSM: Simplifying and Unifying State Space Models for Time Series Forecasting
Hu, Jiaxi
Lan, Disen
Zhou, Ziyu
Wen, Qingsong
Liang, Yuxuan
Machine Learning
Artificial Intelligence
State Space Models (SSMs) have emerged as a potent tool in sequence modeling tasks in recent years. These models approximate continuous systems using a set of basis functions and discretize them to handle input data, making them well-suited for modeling time series data collected at specific frequencies from continuous systems. Despite its potential, the application of SSMs in time series forecasting remains underexplored, with most existing models treating SSMs as a black box for capturing temporal or channel dependencies. To address this gap, this paper proposes a novel theoretical framework termed Dynamic Spectral Operator, offering more intuitive and general guidance on applying SSMs to time series data. Building upon our theory, we introduce Time-SSM, a novel SSM-based foundation model with only one-seventh of the parameters compared to Mamba. Various experiments validate both our theoretical framework and the superior performance of Time-SSM.
title Time-SSM: Simplifying and Unifying State Space Models for Time Series Forecasting
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2405.16312