English
Related papers

Related papers: Benign Overfitting in Single-Head Attention

200 papers

We study transformer language models, analyzing attention heads whose attention patterns are spread out, and whose attention scores depend weakly on content. We argue that the softmax denominators of these heads are stable when the…

Computation and Language · Computer Science 2025-10-07 Alex Gibson

Deep neural networks generalize well despite being exceedingly overparameterized and being trained without explicit regularization. This curious phenomenon has inspired extensive research activity in establishing its statistical principles:…

Machine Learning · Statistics 2021-09-16 Ke Wang , Christos Thrampoulidis

Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of…

Machine Learning · Computer Science 2025-06-19 Parikshit Ram , Kenneth L. Clarkson , Tim Klinger , Shashanka Ubaru , Alexander G. Gray

This study investigates the critical problem of overfitting in deep learning models applied to histopathology image analysis. We show that simply adopting and fine-tuning large-scale models designed for natural image analysis often leads to…

Image and Video Processing · Electrical Eng. & Systems 2025-06-23 Saghir Alfasly , Ghazal Alabtah , H. R. Tizhoosh

Despite the remarkable success of transformer-based models in various real-world tasks, their underlying mechanisms remain poorly understood. Recent studies have suggested that transformers can implement gradient descent as an in-context…

Machine Learning · Computer Science 2024-08-09 Xingwu Chen , Lei Zhao , Difan Zou

When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of the feature detectors on each training case.…

Neural and Evolutionary Computing · Computer Science 2012-07-04 Geoffrey E. Hinton , Nitish Srivastava , Alex Krizhevsky , Ilya Sutskever , Ruslan R. Salakhutdinov

This project investigates the behavior of multi-head attention in Transformer models, specifically focusing on the differences between benign and trojan models in the context of sentiment analysis. Trojan attacks cause models to perform…

Computation and Language · Computer Science 2024-06-26 Jingwei Wang

Neural networks trained with class-imbalanced data are known to perform poorly on minor classes of scarce training data. Several recent works attribute this to over-fitting to minor classes. In this paper, we provide a novel explanation of…

Machine Learning · Computer Science 2021-10-12 Han-Jia Ye , De-Chuan Zhan , Wei-Lun Chao

Overfit is a fundamental problem in machine learning in general, and in deep learning in particular. In order to reduce overfit and improve generalization in the classification of images, some employ invariance to a group of…

Machine Learning · Computer Science 2021-02-12 Roee Cates , Daphna Weinshall

Despite the growing popularity of graph attention mechanisms, their theoretical understanding remains limited. This paper aims to explore the conditions under which these mechanisms are effective in node classification tasks through the…

Machine Learning · Computer Science 2025-05-14 Zhongtian Ma , Qiaosheng Zhang , Bocheng Zhou , Yexin Zhang , Shuyue Hu , Zhen Wang

In the era of deep learning, understanding over-fitting phenomenon becomes increasingly important. It is observed that carefully designed deep neural networks achieve small testing error even when the training error is close to zero. One…

Machine Learning · Statistics 2018-12-04 Yue Xing , Qifan Song , Guang Cheng

We study the training dynamics of gradient descent in a softmax self-attention layer trained to perform linear regression and show that a simple first-order optimization algorithm can converge to the globally optimal self-attention…

Machine Learning · Computer Science 2026-03-03 Gautam Goel , Mahdi Soltanolkotabi , Peter Bartlett

In this paper, we propose a simple and effective technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained…

Computation and Language · Computer Science 2020-10-07 Ameet Deshpande , Karthik Narasimhan

Deep learning models have been widely applied in various aspects of daily life. Many variant models based on deep learning structures have achieved even better performances. Attention-based architectures have become almost ubiquitous in…

Machine Learning · Computer Science 2022-02-25 Zhiying Fang , Yidong Ouyang , Ding-Xuan Zhou , Guang Cheng

The emergence of spontaneous symmetry breaking among a few heads of multi-head attention (MHA) across transformer blocks in classification tasks was recently demonstrated through the quantification of single-nodal performance (SNP). This…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Ronit D. Gross , Tal Halevi , Ella Koresh , Yarden Tzach , Ido Kanter

In the context of neural network models, overparametrization refers to the phenomena whereby these models appear to generalize well on the unseen data, even though the number of parameters significantly exceeds the sample sizes, and the…

Machine Learning · Statistics 2020-03-25 Matt Emschwiller , David Gamarnik , Eren C. Kızıldağ , Ilias Zadik

While large machine learning models have shown remarkable performance in various domains, their training typically requires iterating for many passes over the training data. However, due to computational and memory constraints and potential…

Machine Learning · Computer Science 2025-11-04 Youngjae Min , Namhoon Cho , Navid Azizan

The Transformer is an extremely powerful and prominent deep learning architecture. In this work, we challenge the commonly held belief in deep learning that going deeper is better, and show an alternative design approach that is building…

Machine Learning · Computer Science 2022-11-10 Jason Ross Brown , Yiren Zhao , Ilia Shumailov , Robert D Mullins

Many sequence-to-sequence tasks in natural language processing are roughly monotonic in the alignment between source and target sequence, and previous work has facilitated or enforced learning of monotonic attention behavior via specialized…

Computation and Language · Computer Science 2021-04-09 Annette Rios , Chantal Amrhein , Noëmi Aepli , Rico Sennrich

Supervised fine-tuning (SFT) on domain-specific data is the dominant approach for adapting foundation models to specialized tasks. However, it has been observed that SFT models tend to forget knowledge acquired during pretraining. In vision…

Artificial Intelligence · Computer Science 2025-06-03 Yifan Hao , Xingyuan Pan , Hanning Zhang , Chenlu Ye , Rui Pan , Tong Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›