English
Related papers

Related papers: Krony-PT: GPT2 compressed with Kronecker Products

200 papers

We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization. This space is equipped with a learned…

Machine Learning · Computer Science 2020-02-18 Deniz Oktay , Johannes Ballé , Saurabh Singh , Abhinav Shrivastava

Deep neural networks typically impose significant computational loads and memory consumption. Moreover, the large parameters pose constraints on deploying the model on edge devices such as embedded systems. Tensor decomposition offers a…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Yaping He , Linhao Jiang , Di Wu

While the numerous parameters in Large Language Models (LLMs) contribute to their superior performance, this massive scale makes them inefficient and memory-hungry. Thus, they are hard to deploy on commodity hardware, such as one single…

Computation and Language · Computer Science 2023-10-11 Zhaozhuo Xu , Zirui Liu , Beidi Chen , Yuxin Tang , Jue Wang , Kaixiong Zhou , Xia Hu , Anshumali Shrivastava

In this work we present a method to improve the pruning step of the current state-of-the-art methodology to compress neural networks. The novelty of the proposed pruning technique is in its differentiability, which allows pruning to be…

Computer Vision and Pattern Recognition · Computer Science 2019-01-08 Franco Manessi , Alessandro Rozza , Simone Bianco , Paolo Napoletano , Raimondo Schettini

Large language models have transformed the comprehension and generation of natural language tasks, but they come with substantial memory and computational requirements. Quantization techniques have emerged as a promising avenue for…

Computation and Language · Computer Science 2024-12-10 Amitash Nanda , Sree Bhargavi Balija , Debashis Sahoo

We introduce CUTS-GPR, a new method for performing numerically exact Gaussian process regression (GPR) in high-dimensional settings. The key component of CUTS-GPR is an extremely fast kernel matrix-vector product, which exhibits near-linear…

Machine Learning · Computer Science 2026-05-11 Mads Greisen Højlund , August Smart Lykke-Møller , Henry Moss , Ove Christiansen

Recent large language models (LLMs) employ billions of parameters to enable broad problem-solving capabilities. Such language models also tend to be memory-bound because of the dominance of matrix-vector and matrix-matrix multiplications…

Machine Learning · Computer Science 2024-10-24 Chakshu Moar , Faraz Tahmasebi , Michael Pellauer , Hyoukjun Kwon

Post-training compression of Transformer models commonly relies on truncated singular value decomposition (SVD). However, enforcing a single shared subspace can degrade accuracy even at moderate compression. Sparse dictionary learning…

Machine Learning · Computer Science 2026-02-18 Denis Makhov , Dmitriy Shopkhoev , Magauiya Zhussip , Ammar Ali , Baher Mohammad , Stamatios Lefkimmiatis

This paper introduces DeCAL, a new method for tokenwise compression. DeCAL uses an encoder-decoder language model pretrained with denoising to learn to produce high-quality, general-purpose compressed representations from the encoder. DeCAL…

Computation and Language · Computer Science 2025-10-23 Sameer Panwar

Future cellular systems will likely employ massive bi-dimensional arrays to improve performance by large array gain and more accurate spatial filtering, motivating the design of low-complexity signal processing methods. We propose…

Information Theory · Computer Science 2019-01-29 Lucas N. Ribeiro , André L. F. de Almeida , Josef A. Nossek , João César M. Mota

This paper proposes fast randomized algorithms for computing the Kronecker Tensor Decomposition (KTD). The proposed algorithms can decompose a given tensor into the KTD format much faster than the existing state-of-the-art algorithms. Our…

Numerical Analysis · Mathematics 2025-05-22 Salman Ahmadi-Asl , Naeim Rezaeian , Andre L. F. de Almeida , Yipeng Liu

Chain-of-Thought significantly enhances a model's reasoning capability, but it also comes with a considerable increase in inference costs due to long chains. With the observation that the reasoning path can be easily compressed under easy…

Artificial Intelligence · Computer Science 2025-02-14 Xinyin Ma , Guangnian Wan , Runpeng Yu , Gongfan Fang , Xinchao Wang

The rigidity of a matrix $A$ for target rank $r$ is the minimum number of entries of $A$ that need to be changed in order to obtain a matrix of rank at most $r$. At MFCS'77, Valiant introduced matrix rigidity as a tool to prove circuit…

Data Structures and Algorithms · Computer Science 2021-10-13 Bohdan Kivva

The rapid proliferation of large language models (LLMs) in natural language processing (NLP) has created a critical need for techniques that enable efficient deployment on memory-constrained devices without compromising performance. We…

Computation and Language · Computer Science 2025-02-03 James Seale Smith , Chi-Heng Lin , Shikhar Tuli , Haris Jeelani , Shangqian Gao , Yilin Shen , Hongxia Jin , Yen-Chang Hsu

Large-scale pre-trained language models, such as BERT and GPT-2, have achieved excellent performance in language representation learning and free-form text generation. However, these models cannot be directly employed to generate text under…

Computation and Language · Computer Science 2020-09-29 Yizhe Zhang , Guoyin Wang , Chunyuan Li , Zhe Gan , Chris Brockett , Bill Dolan

Multidimensional NMR inversion using Kronecker products poses several challenges. First, kernel compression is only possible when the kernel matrices are separable, and in recent years, there has been an increasing interest in NMR sequences…

Geophysics · Physics 2016-05-24 David Medellín , Vivek R. Ravi , Carlos Torres-Verdín

Despite the general capabilities of large pretrained language models, they consistently benefit from further adaptation to better achieve desired behaviors. However, tuning these models has become increasingly resource-intensive, or…

Computation and Language · Computer Science 2024-08-26 Alisa Liu , Xiaochuang Han , Yizhong Wang , Yulia Tsvetkov , Yejin Choi , Noah A. Smith

Convolutional neural networks (CNN) have achieved impressive performance on the wide variety of tasks (classification, detection, etc.) across multiple domains at the cost of high computational and memory requirements. Thus, leveraging CNNs…

Computer Vision and Pattern Recognition · Computer Science 2018-11-21 Pravendra Singh , Vinay Sameer Raja Kadi , Nikhil Verma , Vinay P. Namboodiri

We introduce eigenpruning, a method that removes singular values from weight matrices in an LLM to improve its performance in a particular task. This method is inspired by interpretability methods designed to automatically find subnetworks…

Machine Learning · Computer Science 2024-06-21 Tomás Vergara-Browne , Álvaro Soto , Akiko Aizawa

The Tucker decomposition expresses a given tensor as the product of a small core tensor and a set of factor matrices. Apart from providing data compression, the construction is useful in performing analysis such as principal component…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-07-19 Venkatesan T Chakaravarthy , Jee W Choi , Douglas J Joseph , Xing Liu , Prakash Murali , Yogish Sabharwal , Dheeraj Sreedhar