arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.12756cs.LG
收藏

闭环:基于控制理论的具有可证明稳定性的时序预测框架与大语言模型

Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs

University of Chinese Academy of Sciences(中国科学院大学);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所)

Xingyu Zhang, Jingyao Wang, Zeen Song, Changwen Zheng, Wenwen Qiang

AI总结:

本文提出F-LLM框架,通过控制理论方法解决大语言模型在时序预测中的误差累积问题,提供理论保证并实验验证其有效性。

摘要:

大语言模型(LLMs)近期在时序预测中展现出了卓越的潜力,利用其固有的序列推理能力来建模复杂的时序动态。然而,现有方法通常采用一种简单的自回归生成策略。我们发现这一范式中存在一个关键的理论缺陷:在推理过程中,模型以开环方式运行,递归地消耗自身生成的输出。这导致不可避免的误差累积(暴露偏差),其中微小的早期偏差会演变为长期预测中的显著轨迹漂移。在本文中,我们通过控制理论的视角重新构建自回归预测,提出F-LLM(反馈驱动LLM),一种新的闭环框架。与标准方法被动传播误差不同,F-LLM通过可学习的残差估计器(观察器)和反馈控制器主动稳定轨迹。此外,我们提供了一个理论保证,即在基础模型满足局部Lipschitz约束的前提下,我们的闭环机制确保了误差的均匀有界。广泛的实验表明,F-LLM显著减轻了误差传播,实现了在时序基准上的良好表现。

英文摘要:

Large Language Models (LLMs) have recently shown exceptional potential in time series forecasting (TSF), leveraging their inherent sequential reasoning capabilities to model complex temporal dynamics. Existing approaches typically employ an autoregressive generation strategy to adapt LLMs for TSF. However, we identify a theoretical flaw in this paradigm: during inference, the model operates in an open-loop manner, recursively consuming its own generated outputs. This leads to error accumulation, where minor early deviations cascade into significant rollout drift over long horizons. In this paper, we reformulate autoregressive forecasting through the lens of control theory, proposing Feedback-driven LLM (F-LLM), a novel closed-loop framework. Unlike standard methods that passively propagate errors, F-LLM actively stabilizes the trajectory via a learnable residual estimator functioning as a system observer. Furthermore, we provide a mathematical proof that, under explicit contraction assumptions, this closed-loop mechanism guarantees a uniformly bounded step-wise error sequence within the local surrogate dynamics. Extensive experiments demonstrate that F-LLM significantly mitigates error propagation, achieving good performance on time series benchmarks. Our code is publicly available at https://github.com/Zh-XY22/F-LLM.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑