English
Related papers

Related papers: Learning on Transformers is Provable Low-Rank and …

200 papers

Deep neural networks are strongly over-parameterized, often containing far more weights than required for their task. Although such redundancy can aid optimization, it leads to inefficient deployment and high computational cost, motivating…

Disordered Systems and Neural Networks · Physics 2026-02-18 Diego Pesce , Yang-Hui He , Guido Caldarelli

Recent work has highlighted the complex influence training hyperparameters, e.g., the number of training epochs, can have on the prunability of machine learning models. Perhaps surprisingly, a systematic approach to predict precisely how…

Machine Learning · Statistics 2024-03-04 Yefan Zhou , Yaoqing Yang , Arin Chang , Michael W. Mahoney

Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems. In this paper, we tailor transformer-based…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Wenbo Li , Xin Lu , Shengju Qian , Jiangbo Lu , Xiangyu Zhang , Jiaya Jia

Connected and autonomous vehicles continue to heavily rely on AI systems, where transparency and security are critical for trust and operational safety. Post-hoc explanations provide transparency to these black-box like AI models but the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Sanish Suwal , Shaurya Garg , Dipkamal Bhusal , Michael Clifford , Nidhi Rastogi

Sparsity in the structure of Neural Networks can lead to less energy consumption, less memory usage, faster computation times on convenient hardware, and automated machine learning. If sparsity gives rise to certain kinds of structure, it…

Machine Learning · Computer Science 2021-07-28 Julian Stier , Harshil Darji , Michael Granitzer

Deep neural networks have achieved great success in many data processing applications. However, the high computational complexity and storage cost makes deep learning hard to be used on resource-constrained devices, and it is not…

Machine Learning · Computer Science 2023-03-27 Xinwei Ou , Zhangxin Chen , Ce Zhu , Yipeng Liu

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

Overparameterization and overfitting are common concerns when designing and training deep neural networks, that are often counteracted by pruning and regularization strategies. However, these strategies remain secondary to most learning…

Machine Learning · Computer Science 2020-09-01 Malena Reiners , Kathrin Klamroth , Michael Stiglmayr

Sequence modelling requires determining which past tokens are causally relevant from the context and their importance: a process inherent to the attention layers in transformers, yet whose underlying learned mechanisms remain poorly…

Machine Learning · Computer Science 2026-04-14 Francesco D'Angelo , Nicolas Flammarion

Deep convolutional neural networks have liberated its extraordinary power on various tasks. However, it is still very challenging to deploy state-of-the-art models into real-world applications due to their high computational complexity. How…

Computer Vision and Pattern Recognition · Computer Science 2018-09-06 Zehao Huang , Naiyan Wang

Understanding Transformer-based models has attracted significant attention, as they lie at the heart of recent technological advances across machine learning. While most interpretability methods rely on running models over inputs, recent…

Computation and Language · Computer Science 2023-12-27 Guy Dar , Mor Geva , Ankit Gupta , Jonathan Berant

Low-rank approximation is a fundamental technique in modern data analysis, widely utilized across various fields such as signal processing, machine learning, and natural language processing. Despite its ubiquity, the mechanics of low-rank…

Machine Learning · Computer Science 2024-08-13 Jun Lu

Understanding why Transformers perform so well remains challenging due to their non-convex optimization landscape. In this work, we analyze a shallow Transformer with $m$ independent heads trained by projected gradient descent in the kernel…

Machine Learning · Computer Science 2026-04-03 Enes Arda , Semih Cayci , Atilla Eryilmaz

Geometric properties of Transformer weights, particularly the unembedding matrix, have been widely useful in language model interpretability research. Yet, their utility for estimating downstream performance remains unclear. In this work,…

Computation and Language · Computer Science 2026-02-25 Atharva Kulkarni , Jacob Mitchell Springer , Arjun Subramonian , Swabha Swayamdipta

In-context learning (ICL) is a key building block of modern large language models, yet its theoretical mechanisms remain poorly understood. It is particularly mysterious how ICL operates in real-world applications where tasks have a common…

Disordered Systems and Neural Networks · Physics 2026-04-24 Kaito Takanami , Takashi Takahashi , Yoshiyuki Kabashima

We consider the task of building compact deep learning pipelines suitable for deployment on storage and power constrained mobile devices. We propose a unified framework to learn a broad family of structured parameter matrices that are…

Machine Learning · Statistics 2015-10-07 Vikas Sindhwani , Tara N. Sainath , Sanjiv Kumar

Neural network pruning is a popular technique used to reduce the inference costs of modern, potentially overparameterized, networks. Starting from a pre-trained network, the process is as follows: remove redundant parameters, retrain, and…

Machine Learning · Computer Science 2021-03-05 Lucas Liebenwein , Cenk Baykal , Brandon Carter , David Gifford , Daniela Rus

Training large models ranging from millions to billions of parameters is highly resource-intensive, requiring significant time, compute, and memory. It is observed that most of the learning (higher change in weights) takes place in the…

Machine Learning · Computer Science 2026-03-16 Krishu K Thapa , Reet Barik , Krishna Teja Chitty-Venkata , Murali Emani , Venkatram Vishwanath

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

Neural networks have achieved remarkable performance in various application domains. Nevertheless, a large number of weights in pre-trained deep neural networks prohibit them from being deployed on smartphones and embedded systems. It is…

Machine Learning · Computer Science 2023-07-19 Shibo Yao , Dantong Yu , Ioannis Koutis