English
Related papers

Related papers: On the Computational Power of Transformers and its…

200 papers

We find limits to the Transformer architecture for language modeling and show it has a universal prediction property in an information-theoretic sense. We further analyze performance in non-asymptotic data regimes to understand the role of…

Machine Learning · Computer Science 2023-07-18 Sourya Basu , Moulik Choraria , Lav R. Varshney

The remarkable performance of the Transformer architecture in natural language processing has recently also triggered broad interest in Computer Vision. Among other merits, Transformers are witnessed as capable of learning long-range…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Reza Azad , Amirhossein Kazerouni , Moein Heidari , Ehsan Khodapanah Aghdam , Amirali Molaei , Yiwei Jia , Abin Jose , Rijo Roy , Dorit Merhof

Convolutional Neural Networks define an exceptionally powerful class of models, but are still limited by the lack of ability to be spatially invariant to the input data in a computationally and parameter efficient manner. In this work we…

Computer Vision and Pattern Recognition · Computer Science 2016-02-05 Max Jaderberg , Karen Simonyan , Andrew Zisserman , Koray Kavukcuoglu

Transformers are unable to model long-term memories effectively, since the amount of computation they need to perform grows with the context length. While variations of efficient transformers have been proposed, they all have a finite…

Computation and Language · Computer Science 2022-03-28 Pedro Henrique Martins , Zita Marinho , André F. T. Martins

It is common practice to compare the computational power of different models of computation. For example, the recursive functions are strictly more powerful than the primitive recursive functions, because the latter are a proper subset of…

Logic in Computer Science · Computer Science 2020-06-11 Udi Boker , Nachum Dershowitz

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model…

Machine Learning · Computer Science 2023-03-28 Quentin Fournier , Gaétan Marceau Caron , Daniel Aloise

Despite the widespread adoption of Transformer models for NLP tasks, the expressive power of these models is not well-understood. In this paper, we establish that Transformer models are universal approximators of continuous permutation…

Machine Learning · Computer Science 2020-02-26 Chulhee Yun , Srinadh Bhojanapalli , Ankit Singh Rawat , Sashank J. Reddi , Sanjiv Kumar

Understanding the learning process and the embedded computation in transformers is becoming a central goal for the development of interpretable AI. In the present study, we introduce a hierarchical filtering procedure for data models of…

Machine Learning · Computer Science 2025-06-11 Jerome Garnier-Brun , Marc Mézard , Emanuele Moscato , Luca Saglietti

It has been over six years since the Transformer architecture was put forward. Surprisingly, the vanilla Transformer architecture is still widely used today. One reason is that the lack of deep understanding and comprehensive interpretation…

Machine Learning · Computer Science 2023-11-22 Zhe Chen

Transformers, as the fundamental deep learning architecture, have demonstrated great capability in reasoning. This paper studies the generalizable first-order logical reasoning ability of transformers with their parameterized knowledge and…

Computation and Language · Computer Science 2025-07-11 Tianshi Zheng , Jiazheng Wang , Zihao Wang , Jiaxin Bai , Hang Yin , Zheye Deng , Yangqiu Song , Jianxin Li

We study succinctness as a measure of the expressive power of transformers. Succinctness -- how compactly a formalism can describe a language relative to other formalisms -- is a classical notion in logic and automata theory. We prove that…

Formal Languages and Automata Theory · Computer Science 2026-05-18 Pascal Bergsträßer , Ryan Cotterell , Anthony W. Lin

Transformers pretrained via next token prediction learn to factor their world into parts, representing these factors in orthogonal subspaces of the residual stream. We formalize two representational hypotheses: (1) a representation in the…

Formal language theory has recently been successfully employed to unravel the power of transformer encoders. This setting is primarily applicable in Natural Language Processing (NLP), as a token embedding function (where a bounded number of…

Formal Languages and Automata Theory · Computer Science 2024-11-13 Pascal Bergsträßer , Chris Köcher , Anthony Widjaja Lin , Georg Zetzsche

Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the…

Machine Learning · Computer Science 2019-11-13 Yao-Hung Hubert Tsai , Shaojie Bai , Makoto Yamada , Louis-Philippe Morency , Ruslan Salakhutdinov

We propose a new positional encoding method for a neural network architecture called the Transformer. Unlike the standard sinusoidal positional encoding, our approach is based on solid mathematical grounds and has a guarantee of not losing…

Machine Learning · Computer Science 2024-05-17 Tsuyoshi Idé , Jokin Labaien , Pin-Yu Chen

We show that a constant number of self-attention layers can efficiently simulate, and be simulated by, a constant number of communication rounds of Massively Parallel Computation. As a consequence, we show that logarithmic depth is…

Machine Learning · Computer Science 2024-02-15 Clayton Sanford , Daniel Hsu , Matus Telgarsky

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Litao Yu , Jian Zhang

Relative Positional Encoding (RPE), which encodes the relative distance between any pair of tokens, is one of the most successful modifications to the original Transformer. As far as we know, theoretical understanding of the RPE-based…

Machine Learning · Computer Science 2022-10-31 Shengjie Luo , Shanda Li , Shuxin Zheng , Tie-Yan Liu , Liwei Wang , Di He

Transformer, an attention-based encoder-decoder model, has already revolutionized the field of natural language processing (NLP). Inspired by such significant achievements, some pioneering works have recently been done on employing…

Computer Vision and Pattern Recognition · Computer Science 2022-12-07 Yang Liu , Yao Zhang , Yixin Wang , Feng Hou , Jin Yuan , Jiang Tian , Yang Zhang , Zhongchao Shi , Jianping Fan , Zhiqiang He

One of the fundamental results in computability is the existence of well-defined functions that cannot be computed. In this paper we study the effects of data representation on computability; we show that, while for each possible way of…

Computational Complexity · Computer Science 2017-06-30 Jaun Casanova , Simone Santini