arXiv：cs.LG· Weiwei Ye, Renhe Jiang, Hangchen Liu, Dongyuan Li, Yoshihide Sekimoto·· 7 小时前
TimeES：基于演化频谱的概率与确定性时间序列预测框架
TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra
AI 导读
TimeES 是一个基于演化频谱（Evolutionary Spectra）理论的通用时间序列预测框架，可同时支持概率预测与确定性预测，论文已被 NeurIPS 2026 接收为 Poster。
正文
Abstract:Real-world time series are inherently non-stationary, with trends, periodic patterns, and uncertainty evolving over time. While the Fourier domain offers a natural lens to model time series, current deep learning approaches do not explicitly model evolution and randomness in the Fourier spectra, which limits their ability to accurately predict both the expected trajectory and its uncertainty in non-stationary time series. Motivated by Evolutionary Spectra (ES) theory, we propose TimeES, a general framework that enables probabilistic and deterministic forecasting via the evolutionary spectra theory. Specifically, we derive a parameterizable evolutionary spectra formulation, recasting non-stationary random process modeling as learning an evolving representation modulated by random variables. Furthermore, we reduce the complexity of the estimated spectra from O(NM) to O(NK), where K << M/2, by exploiting Hermitian symmetry and spectral energy sparsity for frequency selection. Based on a simple linear backbone, our proposed TimeES achieves consistent state-of-the-art performance across both deterministic and probabilistic forecasting tasks, with high efficiency and interpretability. Code is available at: this https URL.
| Comments: | Accepted as NeurIPS 2026 Poster |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.32384 [cs.LG] |
| (or arXiv:2609.32384v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2609.32384 arXiv-issued DOI via DataCite |
Submission history
From: Weiwei Ye [view email]
[v1]
Sat, 26 Sep 2026 08:58:48 UTC (3,107 KB)
[v2]
Wed, 14 Oct 2026 10:02:53 UTC (3,107 KB)
来源：arXiv：cs.LG · arxiv.org