English
Related papers

Related papers: Why Do Transformers Fail to Forecast Time Series I…

200 papers

Time series forecasting holds significant importance in many real-world dynamic systems and has been extensively studied. Unlike natural language process (NLP) and computer vision (CV), where a single large model can tackle multiple tasks,…

Transformer-based models have demonstrated remarkable reasoning abilities, but the mechanisms underlying relational reasoning remain poorly understood. We investigate how transformers perform \textit{transitive inference}, a classic…

Machine Learning · Computer Science 2026-05-12 Jesse Geerts , Andrew Liu , Stephanie Chan , Claudia Clopath , Kimberly Stachenfeld

Transformer-based models have emerged as promising tools for time series forecasting. However, these model cannot make accurate prediction for long input time series. On the one hand, they failed to capture global dependencies within time…

Machine Learning · Computer Science 2023-08-16 YanJun Zhao , Ziqing Ma , Tian Zhou , Liang Sun , Mengni Ye , Yi Qian

Time series forecasting (TSF) faces challenges in modeling complex intra-channel temporal dependencies and inter-channel correlations. Although recent research has highlighted the efficiency of linear architectures in capturing global…

Machine Learning · Computer Science 2026-01-29 Gawon Lee , Hanbyeol Park , Minseop Kim , Dohee Kim , Hyerim Bae

Transformers have been actively studied for time-series forecasting in recent years. While often showing promising results in various scenarios, traditional Transformers are not designed to fully exploit the characteristics of time-series…

Machine Learning · Computer Science 2022-06-22 Gerald Woo , Chenghao Liu , Doyen Sahoo , Akshat Kumar , Steven Hoi

The quadratic complexity of self attention in Transformer based LLMs renders long context inference prohibitively expensive. While Sliding Window Attention (SWA), the simplest sparse attention pattern, offers a linear complexity…

Computation and Language · Computer Science 2026-03-27 Yijiong Yu , Jiale Liu , Qingyun Wu , Huazheng Wang , Ji Pei

Despite their central role in the success of foundational models and large-scale language modeling, the theoretical foundations governing the operation of Transformers remain only partially understood. Contemporary research has largely…

Machine Learning · Computer Science 2025-06-02 Sagar Ghosh , Kushal Bose , Swagatam Das

Long-term time series forecasting (LTSF) offers broad utility in practical settings like energy consumption and weather prediction. Accurately predicting long-term changes, however, is demanding due to the intricate temporal patterns and…

Machine Learning · Computer Science 2025-05-19 Boshi Gao , Qingjian Ni , Fanbo Ju , Yu Chen , Ziqi Zhao

There has been significant recent interest in understanding the capacity of Transformers for in-context learning (ICL), yet most theory focuses on supervised settings with explicitly labeled pairs. In practice, Transformers often perform…

Machine Learning · Computer Science 2026-02-02 Jiashuo Fan , Paul Rosu , Aaron T. Wang , Zeyu Michael Li , Lawrence Carin , Xiang Cheng

Scaling laws play a central role in the success of Large Language Models (LLMs), enabling the prediction of model performance relative to compute budgets prior to training. While Transformers have been the dominant architecture, recent…

Machine Learning · Computer Science 2026-02-23 Maximilian Beck , Kajetan Schweighofer , Sebastian Böck , Sebastian Lehner , Sepp Hochreiter

In-context learning (ICL) has emerged as an effective approach to enhance the performance of large language models (LLMs). However, its effectiveness varies significantly across models and tasks, posing challenges for practitioners to…

Computation and Language · Computer Science 2025-07-15 Dingzriui Wang , Xuanliang Zhang , Keyan Xu , Qingfu Zhu , Wanxiang Che , Yang Deng

The rapid progress seen in terms of large-scale generative AI is largely based on the attention mechanism. It is conversely non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional…

Machine Learning · Computer Science 2025-08-07 Claudius Gros

Multivariate time series forecasting (MTSF) aims to learn temporal dynamics among variables to forecast future time series. Existing statistical and deep learning-based methods suffer from limited learnable parameters and small-scale…

Machine Learning · Computer Science 2025-04-01 Chenxi Liu , Qianxiong Xu , Hao Miao , Sun Yang , Lingzheng Zhang , Cheng Long , Ziyue Li , Rui Zhao

Time series forecasting at scale presents significant challenges for modern prediction systems, particularly when dealing with large sets of synchronized series, such as in a global payment network. In such systems, three key challenges…

Transformer-based methods have achieved state-of-the-art performance in time series forecasting (TSF) by capturing positional and semantic topological relationships among input tokens. However, it remains unclear whether existing…

Artificial Intelligence · Computer Science 2025-10-27 Jianqi Zhang , Wenwen Qiang , Jingyao Wang , Jiahuan Zhou , Changwen Zheng , Hui Xiong

Time series analysis provides essential insights for real-world system dynamics and informs downstream decision-making, yet most existing methods often overlook the rich contextual signals present in auxiliary modalities. To bridge this…

Machine Learning · Computer Science 2026-03-24 Yushan Jiang , Wenchao Yu , Geon Lee , Dongjin Song , Kijung Shin , Wei Cheng , Yanchi Liu , Haifeng Chen

Time series forecasting plays a critical role in decision-making across many real-world applications. Unlike data in vision and language domains, time series data is inherently tied to the evolution of underlying processes and can only…

Machine Learning · Computer Science 2026-02-03 Suhan Guo , Bingxu Wang , Shaodan Zhang , Furao Shen

Transformers have gained attention in atmospheric time series forecasting (ATSF) for their ability to capture global spatial-temporal correlations. However, their complex architectures lead to excessive parameter counts and extended…

Machine Learning · Computer Science 2025-09-25 Yisong Fu , Fei Wang , Zezhi Shao , Boyu Diao , Lin Wu , Zhulin An , Chengqing Yu , Yujie Li , Yongjun Xu

Pre-trained large language models based on Transformers have demonstrated remarkable in-context learning (ICL) abilities. With just a few demonstration examples, the models can implement new tasks without any parameter updates. However, it…

Machine Learning · Computer Science 2024-11-04 Ruifeng Ren , Yong Liu

Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i.e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior…

Machine Learning · Statistics 2020-09-29 Bryan Lim , Sercan O. Arik , Nicolas Loeff , Tomas Pfister