Abstract:Real-world time series are often governed by complex nonlinear dynamics. Understanding these underlying dynamics is crucial for precise future prediction. While deep learning has achieved major success in time series forecasting, many existing approaches do not explicitly model the dynamics. To bridge this gap, we introduce DeepEDM, a framework that integrates nonlinear dynamical systems modeling with deep neural networks. Inspired by empirical dynamic modeling (EDM) and rooted in Takens' theorem, DeepEDM presents a novel deep model that learns a latent space from time-delayed embeddings, and employs kernel regression to approximate the underlying dynamics, while leveraging efficient implementation of softmax attention and allowing for accurate prediction of future time steps. To evaluate our method, we conduct comprehensive experiments on synthetic data of nonlinear dynamical systems as well as real-world time series across domains. Our results show that DeepEDM is robust to input noise, and outperforms state-of-the-art methods in forecasting accuracy. Our code is available at: this https URL.
| Comments: | Accepted at International Conference on Machine Learning (ICML) 2025 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Machine Learning (stat.ML) |
| Cite as: | arXiv:2506.06454 [cs.LG] |
| (or arXiv:2506.06454v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2506.06454 arXiv-issued DOI via DataCite |
From: Abrar Majeedi [view email]
[v1]
Fri, 6 Jun 2025 18:24:12 UTC (1,066 KB)
[v2]
Thu, 14 Aug 2025 23:19:51 UTC (1,067 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。