轻量高效多变量时间序列预测新模型，精度优于主流方法
Lightweight and Data-Efficient MultivariateTime Series Forecasting using Residual-Stacked Gaussian (RS-GLinear) Architecture
- 基于高斯线性架构改进，引入残差堆叠结构提升建模能力
- 在金融与流行病数据上均实现更优预测精度和鲁棒性
- 适合资源有限但需高精度长期预测的场景
受Transformer在语言建模中捕捉长程依赖的成功启发，研究者尝试将其应用于时间序列预测。尽管已有基于Transformer的模型被提出以处理短时和长时依赖，但如Zeng等（2022）和Rizvi等（2025）所报告，其在长期预测任务中表现参差不齐。本文评估了Rizvi等（2025）提出的基于高斯的线性架构，并提出改进版本——残差堆叠高斯线性（RSGL）模型。我们还验证了该模型在金融时间序列与流行病数据等领域的泛化能力。实验结果表明，相比基准高斯线性模型及Transformer基线，RSGL在预测准确率和鲁棒性方面均有提升。
原文摘要 · Abstract (English)
Following the success of Transformer architectures in language modeling, particularly their ability to capture long-range dependencies, researchers have explored how these architectures can be adapted for time-series forecasting. Transformer-based models have been proposed to handle both short- and long-term dependencies when predicting future values from historical data. However, studies such as those by Zeng et al. (2022) and Rizvi et al. (2025) have reported mixed results in long-term forecasting tasks. In this work, we evaluate the Gaussian-based Linear architecture introduced by Rizvi et al. (2025) and present an enhanced version called the Residual Stacked Gaussian Linear (RSGL) model. We also investigate the broader applicability of the RSGL model in additional domains, including financial time series and epidemiological data. Experimental results show that the RSGL model achieves improved prediction accuracy and robustness compared to both the baseline Gaussian Linear and Transformer-based models.
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。