English
Related papers

Related papers: Beyond Similarity: Temporal Operator Attention for…

200 papers

Transformer-based large language models are in some respects limited by the quadratic time and space computational complexity of attention. We introduce the Toeplitz MLP Mixer (TMM), a transformer-like architecture that swaps attention for…

Machine Learning · Computer Science 2026-05-11 Benjamin L. Badger , Ethan Roland

Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only…

Computation and Language · Computer Science 2021-09-16 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

Autoregressive attention-based time series forecasting (TSF) has drawn increasing interest, with mechanisms like linear attention sometimes outperforming vanilla attention. However, deeper Transformer architectures frequently misalign with…

Machine Learning · Computer Science 2026-02-06 Jiecheng Lu , Shihao Yang

In recent years, Transformer-based models (Transformers) have achieved significant success in multivariate time series forecasting (MTSF). However, previous works focus on extracting features either from the time domain or the frequency…

Machine Learning · Computer Science 2024-11-22 Aobo Liang , Yan Sun , Nadra Guizani

We propose an efficient design of Transformer-based models for multivariate time series forecasting and self-supervised representation learning. It is based on two key components: (i) segmentation of time series into subseries-level patches…

Machine Learning · Computer Science 2023-03-07 Yuqi Nie , Nam H. Nguyen , Phanwadee Sinthong , Jayant Kalagnanam

Transformer architectures have achieved remarkable success in various domains. While efficient alternatives to Softmax Attention have been widely studied, the search for more expressive mechanisms grounded in theoretical insight-even at…

Machine Learning · Computer Science 2025-10-03 Yifei Zuo , Yutong Yin , Zhichen Zeng , Ang Li , Banghua Zhu , Zhaoran Wang

The problem of (point) forecasting $ \textit{univariate} $ time series is considered. Most approaches, ranging from traditional statistical methods to recent learning-based techniques with neural networks, directly operate on raw time…

Machine Learning · Computer Science 2021-07-21 Sebastian Zeng , Florian Graf , Christoph Hofer , Roland Kwitt

We argue that the current practice of evaluating AI/ML time-series forecasting models, predominantly on benchmarks characterized by strong, persistent periodicities and seasonalities, obscures real progress by overlooking the performance of…

Machine Learning · Computer Science 2026-03-17 Raeid Saqur , Christoph Bergmeir , Blanka Horvath , Daniel Schmidt , Frank Rudzicz , Terry Lyons

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.…

Machine Learning · Computer Science 2025-10-14 Yufa Zhou , Yixiao Wang , Surbhi Goel , Anru R. Zhang

Transformers are a widespread and successful model architecture, particularly in Natural Language Processing (NLP) and Computer Vision (CV). The essential innovation of this architecture is the Attention Mechanism, which solves the problem…

Machine Learning · Computer Science 2024-11-25 Bernhard Bermeitinger , Tomas Hrycej , Massimo Pavone , Julianus Kath , Siegfried Handschuh

Transformer models have redefined sequence learning, yet dot-product self-attention introduces a quadratic token-mixing bottleneck for long-context time-series. We introduce the \textbf{Phasor Transformer} block, a phase-native alternative…

Machine Learning · Computer Science 2026-03-19 Dibakar Sigdel

Learning robotic manipulation policies through supervised learning from demonstrations remains challenging when policies encounter execution variations not explicitly covered during training. While incorporating historical context through…

Robotics · Computer Science 2026-03-10 Giovanni Minelli , Giulio Turrisi , Victor Barasuol , Claudio Semini

Transformers excel through content-addressable retrieval and the ability to exploit contexts of, in principle, unbounded length. We recast associative memory at the level of probability measures, treating a context as a distribution over…

Machine Learning · Statistics 2026-02-03 Ryotaro Kawata , Taiji Suzuki

A variety of real-world applications rely on far future information to make decisions, thus calling for efficient and accurate long sequence multivariate time series forecasting. While recent attention-based forecasting models show strong…

Machine Learning · Computer Science 2022-05-02 Razvan-Gabriel Cirstea , Chenjuan Guo , Bin Yang , Tung Kieu , Xuanyi Dong , Shirui Pan

We propose a novel method to sparsify attention in the Transformer model by learning to select the most-informative token representations during the training process, thus focusing on the task-specific parts of an input. A reduction of…

Computation and Language · Computer Science 2022-03-08 Michał Pietruszka , Łukasz Borchmann , Łukasz Garncarek

Standard Transformers excel at semantic modeling but struggle with rigid sequential logic and state tracking. Theoretical work establishes that self-attention is limited to $\AC^0$ (under hard attention) or $\TC^0$ (under soft attention),…

Machine Learning · Computer Science 2026-02-10 Mehryar Mohri

Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer…

Computation and Language · Computer Science 2022-10-12 Xiaofeng Zhang , Yikang Shen , Zeyu Huang , Jie Zhou , Wenge Rong , Zhang Xiong

Softmax attention is the cornerstone of modern large language models, but its memory scales linearly and compute quadratically with sequence length. Linear recurrent models, such as linear attention and state space models, have become…

Machine Learning · Computer Science 2026-05-28 Kevin Y. Li , Asher Trockman , Ananda Theertha Suresh , Ziteng Sun

Time series aggregation (TSA) aims to construct temporally aggregated optimization models that accurately represent the output space of their full-scale counterparts while using a significantly reduced temporal dimensionality. This paper…

Optimization and Control · Mathematics 2026-03-16 Thomas Klatzer , David Cardona-Vasquez , Luca Santosuosso , Sonja Wogrin

Test-Time Adaptation (TTA) enables pre-trained models to adjust to distribution shift by learning from unlabeled test-time streams. However, existing methods typically treat these streams as independent samples, overlooking the supervisory…

Machine Learning · Computer Science 2026-01-30 Young Kyung Kim , Oded Schlesinger , Qiangqiang Wu , J. Matías Di Martino , Guillermo Sapiro
‹ Prev 1 4 5 6 7 8 10 Next ›