English
Related papers

Related papers: Weight-based Decomposition: A Case for Bilinear ML…

200 papers

This work builds together two popular blocks of neural architecture, namely convolutional layers and Transformers, for large language models (LLMs). Non-causal conformers are used ubiquitously in automatic speech recognition. This work aims…

Computation and Language · Computer Science 2023-07-04 Prateek Verma

Many machine learning applications use latent variable models to explain structure in data, whereby visible variables (= coordinates of the given datapoint) are explained as a probabilistic function of some hidden variables. Finding…

Machine Learning · Computer Science 2016-12-30 Sanjeev Arora , Rong Ge , Tengyu Ma , Andrej Risteski

The great advances of learning-based approaches in image processing and computer vision are largely based on deeply nested networks that compose linear transfer functions with suitable non-linearities. Interestingly, the most frequently…

Computer Vision and Pattern Recognition · Computer Science 2018-03-26 Peter Ochs , Tim Meinhardt , Laura Leal-Taixe , Michael Moeller

Linear attention methods offer a compelling alternative to softmax attention due to their efficiency in recurrent decoding. Recent research has focused on enhancing standard linear attention by incorporating gating while retaining its…

Machine Learning · Computer Science 2025-04-08 Yingcong Li , Davoud Ataee Tarzanagh , Ankit Singh Rawat , Maryam Fazel , Samet Oymak

Large Language Models (LLMs) are known for their performance, but we uncover a significant structural inefficiency: a phenomenon we term attention collapse. In many pre-trained decoder-style LLMs, the attention matrices in deeper layers…

Computation and Language · Computer Science 2026-02-17 Sunny Sanyal , Ravid Shwartz-Ziv , Alexandros G. Dimakis , Sujay Sanghavi

Tensor decomposition methods are widely used for model compression and fast inference in convolutional neural networks (CNNs). Although many decompositions are conceivable, only CP decomposition and a few others have been applied in…

Machine Learning · Computer Science 2019-11-28 Kohei Hayashi , Taiki Yamaguchi , Yohei Sugawara , Shin-ichi Maeda

In this paper, we propose to employ a bank of modality-dedicated Convolutional Neural Networks (CNNs), fuse, train, and optimize them together for person classification tasks. A modality-dedicated CNN is used for each modality to extract…

Machine Learning · Computer Science 2018-07-04 Sobhan Soleymani , Amirsina Torfi , Jeremy Dawson , Nasser M. Nasrabadi

Transformers have become one of the most important architectural innovations in deep learning and have enabled many breakthroughs over the past few years. Here we propose a simple network architecture, gMLP, based on MLPs with gating, and…

Machine Learning · Computer Science 2021-06-03 Hanxiao Liu , Zihang Dai , David R. So , Quoc V. Le

Recent works have shown that imposing tensor structures on the coefficient tensor in regression problems can lead to more reliable parameter estimation and lower sample complexity compared to vector-based methods. This work investigates a…

Machine Learning · Statistics 2023-08-08 Batoul Taki , Anand D. Sarwate , Waheed U. Bajwa

In this technical report, we analyze Legendre decomposition for non-negative tensor in theory and application. In theory, the properties of dual parameters and dually flat manifold in Legendre decomposition are reviewed, and the process of…

Machine Learning · Computer Science 2020-09-22 Jianye Pang , Kai Yi , Wanguang Yin , Min Xu

Vision language models (VLMs) excel in multimodal understanding but are prone to adversarial attacks. Existing defenses often demand costly retraining or significant architecture changes. We introduce a lightweight defense using tensor…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Het Patel , Muzammil Allie , Qian Zhang , Jia Chen , Evangelos E. Papalexakis

Binary neural networks have attracted numerous attention in recent years. However, mainly due to the information loss stemming from the biased binarization, how to preserve the accuracy of networks still remains a critical issue. In this…

Computer Vision and Pattern Recognition · Computer Science 2020-02-12 Mingzhu Shen , Xianglong Liu , Ruihao Gong , Kai Han

Although large language models (LLMs) have achieved revolutionary breakthroughs in many fields, their large model size and high computational cost pose significant challenges for practical deployment on resource-constrained edge devices. To…

Machine Learning · Computer Science 2025-10-29 Yao Lu , Yuqi Li , Wenbin Xie , Shanqing Yu , Qi Xuan , Zhaowei Zhu , Shiping Wen

Quantizing large language models has become a standard way to reduce their memory and computational costs. Typically, existing methods focus on breaking down the problem into individual layer-wise sub-problems, and minimizing per-layer…

Machine Learning · Computer Science 2024-11-27 Vladimir Malinovskii , Andrei Panferov , Ivan Ilin , Han Guo , Peter Richtárik , Dan Alistarh

While current state-of-the-art generalizable implicit neural shape models rely on the inductive bias of convolutions, it is still not entirely clear how properties emerging from such biases are compatible with the task of 3D reconstruction…

Computer Vision and Pattern Recognition · Computer Science 2023-11-22 Amine Ouasfi , Adnane Boukhayma

ReLU neural networks have been modelled as constraints in mixed integer linear programming (MILP), enabling surrogate-based optimisation in various domains and efficient solution of machine learning certification problems. However, previous…

Optimization and Control · Mathematics 2023-12-05 Tom McDonald , Calvin Tsay , Artur M. Schweidtmann , Neil Yorke-Smith

In neural network compression, most current methods reduce unnecessary parameters by measuring importance and redundancy. To augment already highly optimized existing solutions, we propose linearity-based compression as a novel way to…

Machine Learning · Computer Science 2025-06-27 Silas Dobler , Florian Lemmerich

In this paper, we present the first structural binarization method for LLM compression to less than 1-bit precision. Although LLMs have achieved remarkable performance, their memory-bound nature during the inference stage hinders the…

Machine Learning · Computer Science 2024-10-10 Peijie Dong , Lujun Li , Yuedong Zhong , Dayou Du , Ruibo Fan , Yuhan Chen , Zhenheng Tang , Qiang Wang , Wei Xue , Yike Guo , Xiaowen Chu

Gated Linear Units (GLU) have shown great potential in enhancing neural network performance. In this paper, I introduce a novel attention mechanism called GLU Attention, which introduces nonlinearity into the values of Attention. My…

Machine Learning · Computer Science 2025-07-08 Zehao Wang

Large language models (LLMs) significantly enhance the performance of various applications, but they are computationally intensive and energy-demanding. This makes it challenging to deploy them on devices with limited resources, such as…

Machine Learning · Computer Science 2025-12-22 Yang Li , Daniel Agyei Asante , Changsheng Zhao , Ernie Chang , Yangyang Shi , Vikas Chandra