导读语:
问题是当前一个热点性的研究问题,本篇博客介绍了清华软院龙老师团队2023年的一项研究。
论文阅读 | 名称 |
---|---|
英文名称 | Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors |
中文名称 | Koopa:基于Koopman预测器的非平稳时间序列动力学学习方法 |
作者 | 清华软院(龙明盛老师团队) |
论文阅读-Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors
1. 摘要
原文:
Real-world time series are characterized by intrinsic non-stationarity that poses a principal challenge for deep forecasting models. While previous models suffer from complicated series variations induced by changing temporal distribution, we tackle non-stationary time series with modern Koopman theory that fundamentally considers the underlying time-variant dynamics. Inspired by Koopman theory that portrays complex dynamical systems, we disentangle time-variant and time invariant compon