English
Related papers

Related papers: Provably learning a multi-head attention layer

200 papers

The Transformer is a sequence model that forgoes traditional recurrent architectures in favor of a fully attention-based approach. Besides improving performance, an advantage of using attention is that it can also help to interpret a model…

Human-Computer Interaction · Computer Science 2019-06-14 Jesse Vig

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…

Machine Learning · Statistics 2026-03-18 Nuri Mert Vural , Alberto Bietti , Mahdi Soltanolkotabi , Denny Wu

Recent research has explored the memorization capacity of multi-head attention, but these findings are constrained by unrealistic limitations on the context size. We present a novel proof for language-based Transformers that extends the…

Artificial Intelligence · Computer Science 2025-03-11 Léo Dana , Muni Sreenivas Pydi , Yann Chevaleyre

Attention layers are an integral part of modern end-to-end automatic speech recognition systems, for instance as part of the Transformer or Conformer architecture. Attention is typically multi-headed, where each head has an independent set…

Computation and Language · Computer Science 2022-09-14 Kartik Audhkhasi , Yinghui Huang , Bhuvana Ramabhadran , Pedro J. Moreno

In modern machine learning, inner product attention computation is a fundamental task for training large language models such as Transformer, GPT-1, BERT, GPT-2, GPT-3 and ChatGPT. Formally, in this problem, one is given as input three…

Machine Learning · Computer Science 2023-05-11 Josh Alman , Zhao Song

Attention, specifically scaled dot-product attention, has proven effective for natural language, but it does not have a mechanism for handling hierarchical patterns of arbitrary nesting depth, which limits its ability to recognize certain…

Computation and Language · Computer Science 2024-01-25 Brian DuSell , David Chiang

Transformers serve as the foundation of most modern large language models. To mitigate the quadratic complexity of standard full attention, various efficient attention mechanisms, such as linear and hybrid attention, have been developed. A…

Machine Learning · Computer Science 2026-02-03 Xiaowei Ye , Xiaoyu He , Chao Liao , Chen Wu , Pinyan Lu

Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long…

Machine Learning · Computer Science 2019-07-03 Sainbayar Sukhbaatar , Edouard Grave , Guillaume Lample , Herve Jegou , Armand Joulin

We investigate the in-context learning capabilities of transformers for the $d$-dimensional mixture of linear regression model, providing theoretical insights into their existence, generalization bounds, and training dynamics. Specifically,…

Machine Learning · Statistics 2025-02-11 Yanhao Jin , Krishnakumar Balasubramanian , Lifeng Lai

Recent progress has rapidly advanced our understanding of the mechanisms underlying in-context learning in modern attention-based neural networks. However, existing results focus exclusively on unimodal data; in contrast, the theoretical…

Machine Learning · Statistics 2026-05-19 Nicholas Barnfield , Subhabrata Sen , Pragya Sur

We study the capacity of the self-attention key-query channel: for a fixed budget, how many distinct token-token relations can a single layer reliably encode? We introduce Relational Graph Recognition, where the key-query channel encodes a…

Machine Learning · Computer Science 2026-02-04 Micah Adler

With the attention mechanism, transformers achieve significant empirical successes. Despite the intuitive understanding that transformers perform relational inference over long sequences to produce desirable representations, we lack a…

Machine Learning · Computer Science 2024-04-02 Yufeng Zhang , Boyi Liu , Qi Cai , Lingxiao Wang , Zhaoran Wang

Large language model (LLM) inference is increasingly bottlenecked by the Key-Value (KV) cache, yet the fine-grained structure of attention-head activations remains poorly understood. We show that pretrained Transformers exhibit a pervasive…

Machine Learning · Computer Science 2026-03-17 Khalid Shaikh , Asmit Kumar Singh , Rebecca Christopher Dsouza , Shikhar Shiromani

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements of the model capabilities. Yet, a theoretical characterization…

Machine Learning · Computer Science 2025-02-10 Hugo Cui , Freya Behrens , Florent Krzakala , Lenka Zdeborová

Sequence-to-sequence (encoder-decoder) models with attention constitute a cornerstone of deep learning research, as they have enabled unprecedented sequential data modeling capabilities. This effectiveness largely stems from the capacity of…

Artificial Intelligence · Computer Science 2018-10-31 Aristotelis Charalampous , Sotirios Chatzis

In this paper we propose augmenting Vision Transformer models with learnable memory tokens. Our approach allows the model to adapt to new tasks, using few parameters, while optionally preserving its capabilities on previously learned tasks.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Mark Sandler , Andrey Zhmoginov , Max Vladymyrov , Andrew Jackson

Transformers have reshaped machine learning by utilizing attention mechanisms to capture complex patterns in large datasets, leading to significant improvements in performance. This success has contributed to the belief that "bigger means…

Machine Learning · Computer Science 2025-05-28 Hemanth Saratchandran , Damien Teney , Simon Lucey

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Hardware Architecture · Computer Science 2025-01-15 Rya Sanovar , Srikant Bharadwaj , Renee St. Amant , Victor Rühle , Saravan Rajmohan

The self-attention mechanism has significantly advanced the field of natural language processing, facilitating the development of advanced language-learning machines. Although its utility is widely acknowledged, the precise mechanisms of…

Computation and Language · Computer Science 2026-02-04 Tal Halevi , Yarden Tzach , Ronit D. Gross , Shalom Rosner , Ido Kanter