English
Related papers

Related papers: Max-Margin Token Selection in Attention Mechanism

200 papers

We study the hardmax limit of self-attention dynamics for token embeddings obtained in the zero-temperature ($\beta\to+\infty$) regime, and relate it to the finite-$\beta$ setting. In this limit, the update rule can be viewed as a…

Optimization and Control · Mathematics 2025-08-14 Albert Alcalde , Borjan Geshkovski , Domènec Ruiz-Balet

Attention mechanisms have become a popular component in deep neural networks, yet there has been little examination of how different influencing factors and methods for computing attention from these factors affect performance. Toward a…

Computer Vision and Pattern Recognition · Computer Science 2019-04-15 Xizhou Zhu , Dazhi Cheng , Zheng Zhang , Stephen Lin , Jifeng Dai

Reinforcement-learning-based post-training has become a key approach for improving the reasoning ability of large language models, but its token-level learning signals remain poorly understood. This work studies their heterogeneity through…

Computation and Language · Computer Science 2026-05-11 Gengyang Li , Zheng-Fan Wu , Siqi Bao , Yunfang Wu

Speech Emotion Recognition (SER) plays a key role in advancing human-computer interaction. Attention mechanisms have become the dominant approach for modeling emotional speech due to their ability to capture long-range dependencies and…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-17 Marc Casals-Salvador , Federico Costa , Rodolfo Zevallos , Javier Hernando

While Transformers have shown remarkable success in natural language processing, their attention mechanism's large memory requirements have limited their ability to handle longer contexts. Prior approaches, such as recurrent memory or…

Computation and Language · Computer Science 2023-11-21 Amirkeivan Mohtashami , Martin Jaggi

Practitioners have consistently observed three puzzling phenomena in transformer-based large language models (LLMs): attention sinks, value-state drains, and residual-state peaks, collectively referred to as extreme-token phenomena. These…

Machine Learning · Computer Science 2024-11-08 Tianyu Guo , Druv Pai , Yu Bai , Jiantao Jiao , Michael I. Jordan , Song Mei

Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism, a core component of transformers, has proven capable of handling complex data…

Machine Learning · Computer Science 2025-08-05 Laziz Abdullaev , Tan M. Nguyen

The self-attention mechanism (SAM) is widely used in various fields of artificial intelligence and has successfully boosted the performance of different models. However, current explanations of this mechanism are mainly based on intuitions…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Zhongzhan Huang , Mingfu Liang , Jinghui Qin , Shanshan Zhong , Liang Lin

Attention layers are the core component of transformers, the current state-of-the-art neural network architecture. Alternatives to softmax-based attention are being explored due to its tendency to hinder effective information flow. Even at…

Machine Learning · Computer Science 2025-06-17 Thiziri Nait Saada , Alireza Naderi , Jared Tanner

Linear attention has attracted interest as a computationally efficient approximation to softmax attention, especially for long sequences. Recent studies have explored distilling softmax attention in pre-trained Transformers into linear…

Machine Learning · Computer Science 2025-07-08 Naoki Nishikawa , Rei Higuchi , Taiji Suzuki

Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability of capturing short- and long-range visual dependencies through self-attention is arguably the main source for the success.…

Computer Vision and Pattern Recognition · Computer Science 2021-07-02 Jianwei Yang , Chunyuan Li , Pengchuan Zhang , Xiyang Dai , Bin Xiao , Lu Yuan , Jianfeng Gao

We study the spectral properties of sample covariance matrices constructed from pooled sequence representations, where token embeddings are drawn from a fixed two-class Gaussian mixture table and pooled via (fixed) attention weights.…

Machine Learning · Statistics 2026-05-11 Mohamed El Amine Seddik

Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less explored due to the optimization difficulties or complicated…

Machine Learning · Computer Science 2021-06-10 Shujian Zhang , Xinjie Fan , Bo Chen , Mingyuan Zhou

Self-attention mechanisms are foundational to Transformer architectures, supporting their impressive success in a wide range of tasks. While there are many self-attention variants, their robustness to noise and spurious correlations has not…

Machine Learning · Computer Science 2025-09-09 Camilo Tamayo-Rousseau , Yunjia Zhao , Yiqun Zhang , Randall Balestriero

The self-attention mechanism is the key to the success of transformers in recent Large Language Models (LLMs). However, the quadratic computational cost $O(n^2)$ in the input sequence length $n$ is a notorious obstacle for further…

Machine Learning · Computer Science 2024-10-17 Yingyu Liang , Heshan Liu , Zhenmei Shi , Zhao Song , Zhuoyan Xu , Junze Yin

The Transformer architecture, a cornerstone of modern Large Language Models (LLMs), has achieved extraordinary success in sequence modeling, primarily due to its attention mechanism. However, despite its power, the standard attention…

Machine Learning · Computer Science 2026-01-08 Zichuan Fu , Wentao Song , Guojing Li , Yejing Wang , Xian Wu , Yimin Deng , Hanyu Yan , Yefeng Zheng , Xiangyu Zhao

Large Language Models (LLMs) are increasingly prevalent in the field of long-context modeling, however, their inference computational costs have become a critical bottleneck hindering the advancement of tasks such as agents and multimodal…

Computation and Language · Computer Science 2025-12-04 Di Xiu , Hongyin Tang , Bolin Rong , Lizhi Yan , Jingang Wang , Yifan Lu , Xunliang Cai

Despite powering modern AI, transformers remain mysteriously brittle to train. We develop a stability theory that explains why pre-LayerNorm works, why DeepNorm uses $N^{-1/4}$ scaling, and why warmup is necessary, all from first…

Machine Learning · Computer Science 2026-02-24 Seyed Morteza Emadi

We examine gradient descent on unregularized logistic regression problems, with homogeneous linear predictors on linearly separable datasets. We show the predictor converges to the direction of the max-margin (hard margin SVM) solution. The…

Machine Learning · Statistics 2024-10-29 Daniel Soudry , Elad Hoffer , Mor Shpigel Nacson , Suriya Gunasekar , Nathan Srebro

With an eye toward understanding complexity control in deep learning, we study how infinitesimal regularization or gradient descent optimization lead to margin maximizing solutions in both homogeneous and non-homogeneous models, extending…

Machine Learning · Statistics 2019-05-20 Mor Shpigel Nacson , Suriya Gunasekar , Jason D. Lee , Nathan Srebro , Daniel Soudry
‹ Prev 1 3 4 5 6 7 10 Next ›