English
Related papers

Related papers: Average Attention Transformers and Arithmetic Circ…

200 papers

Attention-based mechanisms are widely used in machine learning, most prominently in transformers. However, hyperparameters such as the rank of the attention matrices and the number of heads are scaled nearly the same way in all realizations…

Machine Learning · Computer Science 2024-07-24 Noah Amsel , Gilad Yehudai , Joan Bruna

Attention is a key component of Transformers, which have recently achieved considerable success in natural language processing. Hence, attention is being extensively studied to investigate various linguistic capabilities of Transformers,…

Computation and Language · Computer Science 2020-10-07 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits…

Computation and Language · Computer Science 2016-09-28 Lei Yu , Jan Buys , Phil Blunsom

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

We present an architecture that is effective for continual learning in an especially demanding setting, where task boundaries do not exist or are unknown, and where classes have to be learned online (with each example presented only once).…

Machine Learning · Computer Science 2021-10-08 Murray Shanahan , Christos Kaplanis , Jovana Mitrović

Attention architectures are widely used; they recently gained renewed popularity with Transformers yielding a streak of state of the art results. Yet, the geometrical implications of softmax-attention remain largely unexplored. In this work…

Machine Learning · Computer Science 2020-05-20 Oliver Richter , Roger Wattenhofer

Transformers have had tremendous impact for several sequence related tasks, largely due to their ability to retrieve from any part of the sequence via softmax based dot-product attention. This mechanism plays a crucial role in Transformer's…

Machine Learning · Computer Science 2025-07-15 Sai Surya Duvvuri , Inderjit S. Dhillon

VRAM requirements for transformer models scale quadratically with context length due to the self-attention mechanism. In this paper we modify the decoder-only transformer, replacing self-attention with InAttention, which scales linearly…

Machine Learning · Computer Science 2024-10-10 Joseph Eisner

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto

Tensor Attention, a multi-view attention that is able to capture high-order correlations among multiple modalities, can overcome the representational limitations of classical matrix attention. However, the $O(n^3)$ time complexity of tensor…

Machine Learning · Computer Science 2026-01-27 Yang Cao , Yingyu Liang , Zhenmei Shi , Zhao Song

We present a general method for approximately contracting tensor networks with an arbitrary connectivity. This enables us to release the computational power of tensor networks to wide use in inference and learning problems defined on…

Computational Physics · Physics 2020-08-12 Feng Pan , Pengfei Zhou , Sujie Li , Pan Zhang

Transformers have been proven a successful model for a variety of tasks in sequence modeling. However, computing the attention matrix, which is their key component, has quadratic complexity with respect to the sequence length, thus making…

Machine Learning · Computer Science 2020-10-01 Apoorv Vyas , Angelos Katharopoulos , François Fleuret

We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsity regularisation under a constrained-loss objective, we show on models up to 7B parameters that…

Machine Learning · Computer Science 2026-05-26 Florent Draye , Anson Lei , Hsiao-Ru Pan , Ingmar Posner , Bernhard Schölkopf

The Transformer architecture is widely deployed in many popular and impactful Large Language Models. At its core is the attention mechanism for calculating correlations between pairs of tokens. Performing an attention computation takes…

Machine Learning · Computer Science 2025-05-26 Josh Alman , Hantao Yu

Dense prediction tasks have enjoyed a growing complexity of encoder architectures, decoders, however, have remained largely the same. They rely on individual blocks decoding intermediate feature maps sequentially. We introduce banks, shared…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Frederik Laboyrie , Mehmet Kerim Yucel , Albert Saa-Garriga

We derive a rigorous upper bound on the classical computation time of finite-ranged tensor network contractions in $d \geq 2$ dimensions. Consequently, we show that quantum circuits of single-qubit and finite-ranged two-qubit gates can be…

Quantum Physics · Physics 2023-11-07 Thorsten B. Wahl , Sergii Strelchuk

We highlight a perhaps important but hitherto unobserved insight: The attention module in a transformer is a smoothed cubic spline. Viewed in this manner, this mysterious but critical component of a transformer becomes a natural development…

Artificial Intelligence · Computer Science 2024-08-20 Zehua Lai , Lek-Heng Lim , Yucong Liu

Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the model to learn alignments between the source and the target…

Computation and Language · Computer Science 2017-11-06 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

Despite that going deep has proven successful in many neural architectures, the existing graph transformers are relatively shallow. In this work, we explore whether more layers are beneficial to graph transformers, and find that current…

Machine Learning · Computer Science 2023-03-02 Haiteng Zhao , Shuming Ma , Dongdong Zhang , Zhi-Hong Deng , Furu Wei

Attention mechanisms have become a standard tool for sequence modeling tasks, in particular by stacking self-attention layers over the entire input sequence as in the Transformer architecture. In this work we introduce a novel attention…

Machine Learning · Computer Science 2021-06-09 Da Ju , Stephen Roller , Sainbayar Sukhbaatar , Jason Weston