paper-with-me

홈 › Papers

Why Do Transformers Fail to Forecast Time Series In-Context?

2025-10-10 · Yufa Zhou, Yixiao Wang, Surbhi Goel, Anru R. Zhang arxiv

Time series forecasting (TSF) remains a challenging and largely unsolved problem in machine learning, despite significant recent efforts leveraging Large Language Models (LLMs), which predominantly rely on Transformer architectures. Empirical evidence consistently shows that even powerful Transformers often fail to outperform much simpler models, e.g., linear models, on TSF tasks; however, a rigorous theoretical understanding of this phenomenon remains limited. In this paper, we provide a theoretical analysis of Transformers' limitations for TSF through the lens of In-Context Learning (ICL) theory. Specifically, under AR($p$) data, we establish that: (1) Linear Self-Attention (LSA) models $\textit{cannot}$ achieve lower expected MSE than classical linear models for in-context forecasting; (2) as the context length approaches to infinity, LSA asymptotically recovers the optimal linear predictor; and (3) under Chain-of-Thought (CoT) style inference, predictions collapse to the mean exponentially. We empirically validate these findings through carefully designed experiments. Our theory not only sheds light on several previously underexplored phenomena but also offers practical insights for designing more effective forecasting architectures. We hope our work encourages the broader research community to revisit the fundamental theoretical limitations of TSF and to critically evaluate the direct application of increasingly sophisticated architectures without deeper scrutiny.

📄 PDF Abstract BibTeX arXiv:2510.09776

Code (0)

등록된 구현이 없습니다.

Tasks

Time Series Forecasting

Similar Papers 제목 키워드 기반

Why Attention Fails: The Degeneration of Transformers into MLPs in Time Series Forecasting

2025-09-25 · Zida Liang, Jiayi Zhu, Weiqiang Sun arxiv

Transformer-based architectures achieved high performance in natural language processing and computer vision, yet many studies have shown that they have not demonstrated a clear advantage in time series forecasting and e…

Time Series Forecasting

Timer-XL: Long-Context Transformers for Unified Time Series Forecasting

2024-10-07 · Yong liu, Guo Qin, Xiangdong Huang, Jianmin Wang 외

We present Timer-XL, a generative Transformer for unified time series forecasting. To uniformly predict 1D and 2D time series, we generalize next token prediction, predominantly adopted for causal generation of 1D sequen…

Time SeriesTime Series Forecasting

Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond

2024-12-08 · Yekun Ke, YIngyu Liang, Zhenmei Shi, Zhao Song 외

The application of transformer-based models on time series forecasting (TSF) tasks has long been popular to study. However, many of these works fail to beat the simple linear residual model, and the theoretical understan…

AttributeTime SeriesTime Series Forecasting

Financial Time Series Forecasting using CNN and Transformer

2023-04-11 · Zhen Zeng, Rachneet Kaur, Suchetha Siddagangappa, Saba Rahimi 외

Time series forecasting is important across various domains for decision-making. In particular, financial time series such as stock prices can be hard to predict as it is difficult to model short-term and long-term tempo…

Decision MakingTime SeriesTime Series Forecasting

Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworks

2022-02-22 · Wenying Duan, Xiaoxi He, Lu Zhou, Lothar Thiele 외

Time series forecasting has widespread applications in urban life ranging from air quality monitoring to traffic analysis. However, accurate time series forecasting is challenging because real-world time series suffer fr…

Domain AdaptationTime SeriesTime Series AnalysisTime Series Forecasting