English
Related papers

Related papers: Optimal Brain Decomposition for Accurate LLM Low-R…

200 papers

Large language models (LLMs) face significant computational and memory challenges, making extremely low-bit quantization crucial for their efficient deployment. In this work, we introduce SDQ-LLM: Sigma-Delta Quantization for 1-bit LLMs of…

Machine Learning · Computer Science 2025-10-07 Junhao Xia , Ming Zhao , Limin Xiao , Xiujun Zhang

Recent advances in Large Language Model (LLM) compression, such as quantization and pruning, have achieved notable success. However, as these techniques gradually approach their respective limits, relying on a single method for further…

Computation and Language · Computer Science 2025-09-17 Hang Guo , Yawei Li , Luca Benini

Computing eigenvalue decomposition (EVD) of a given linear operator, or finding its leading eigenvalues and eigenfunctions, is a fundamental task in many machine learning and scientific computing problems. For high-dimensional eigenvalue…

Machine Learning · Computer Science 2024-08-22 J. Jon Ryu , Xiangxiang Xu , H. S. Melihcan Erol , Yuheng Bu , Lizhong Zheng , Gregory W. Wornell

Large language models (LLM) and vision-language models (VLM) have achieved state-of-the-art performance, but they impose significant memory and computing challenges in deployment. We present a novel low-rank compression framework to address…

Computation and Language · Computer Science 2025-10-08 Ryan Solgi , Parsa Madinei , Jiayi Tian , Rupak Swaminathan , Jing Liu , Nathan Susanj , Zheng Zhang

The massive scaling of Large Language Models (LLMs) has made pretraining increasingly cost-prohibitive. While low-rank representation and orthonormal weight matrices could in principle reduce parameter counts and computational overhead,…

Machine Learning · Computer Science 2026-05-28 Kaivan Kamali , Kajetan Schweighofer , Hormoz Shahrzad , Olivier Francon , Babak Hodjat , Risto Miikkulainen

The rapid growth in the parameter scale of large language models (LLMs) has created a high demand for efficient compression techniques. As a hardware-agnostic and highly compatible technique, low-rank compression has been widely adopted.…

Computation and Language · Computer Science 2026-02-04 Xing Hu , Dawei Yang , Yuan Cheng , Zhixuan Chen , Zukang Xu

As a type of pseudoinverse learning, extreme learning machine (ELM) is able to achieve high performances in a rapid pace on benchmark datasets. However, when it is applied to real life large data, decline related to low-convergence of…

Machine Learning · Computer Science 2019-07-29 Apdullah Yayık , Yakup Kutlu , Gökhan Altan

Large language models (LLMs) have achieved remarkable success in natural language processing (NLP) tasks, yet their substantial memory requirements present significant challenges for deployment on resource-constrained devices. Singular…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Zhiteng Li , Mingyuan Xia , Jingyuan Zhang , Zheng Hui , Haotong Qin , Linghe Kong , Yulun Zhang , Xiaokang Yang

Singular value decomposition (SVD) has a crucial role in model order reduction. It is often utilized in the offline stage to compute basis functions that project the high-dimensional nonlinear problem into a low-dimensionsl model which is,…

Numerical Analysis · Mathematics 2016-11-09 Alessandro Alla , J. Nathan Kutz

Open-vocabulary object detection (OVD) models are considered to be Large Multi-modal Models (LMM), due to their extensive training data and a large number of parameters. Mainstream OVD models prioritize object coarse-grained category rather…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Yuqi Ma , Mengyin Liu , Chao Zhu , Xu-Cheng Yin

This paper investigates the under-explored area of low-rank weight training for large-scale Conformer-based speech recognition models from scratch. Our study demonstrates the viability of this training paradigm for such models, yielding…

Sound · Computer Science 2024-10-11 Adriana Fernandez-Lopez , Shiwei Liu , Lu Yin , Stavros Petridis , Maja Pantic

We propose a compression based continual task learning method that can dynamically grow a neural network. Inspired from the recent model compression techniques, we employ compression-aware training and perform low-rank weight approximations…

Computer Vision and Pattern Recognition · Computer Science 2020-09-16 Varigonda Pavan Teja , Priyadarshini Panda

This study explores the learning dynamics of neural networks by analyzing the singular value decomposition (SVD) of their weights throughout training. Our investigation reveals that an orthogonal basis within each multidimensional weight's…

Machine Learning · Computer Science 2024-11-12 Daniel Coquelin , Katharina Flügel , Marie Weiel , Nicholas Kiefer , Charlotte Debus , Achim Streit , Markus Götz

An efficient, accurate and reliable approximation of a matrix by one of lower rank is a fundamental task in numerical linear algebra and signal processing applications. In this paper, we introduce a new matrix decomposition approach termed…

Numerical Analysis · Computer Science 2018-08-15 Maboud F. Kaloorazi , Rodrigo C. de Lamare

The Key-Value (KV) cache is central to the efficiency of transformer-based large language models (LLMs), storing previously computed vectors to accelerate inference. Yet, as sequence length and batch size grow, the cache becomes a major…

Machine Learning · Computer Science 2025-12-08 Damien Lesens , Beheshteh T. Rakhshan , Guillaume Rabusseau

Most existing structured pruning methods for Large Language Models (LLMs) require substantial computational and data resources for retraining to reestablish the corrupted correlations, making them prohibitively expensive. To address this,…

Computation and Language · Computer Science 2025-06-11 Jiujun He , Huazhen Lin

Large language models (LLMs) with extended context windows enable powerful downstream applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly with sequence length and batch size. Existing…

Computation and Language · Computer Science 2025-10-10 Yuzhe Gu , Xiyu Liang , Jiaojiao Zhao , Enmao Diao

To improve the training efficiency of federated learning (FL), previous research has employed low-rank decomposition techniques to reduce communication overhead. In this paper, we seek to enhance the performance of these low-rank…

Machine Learning · Computer Science 2025-08-19 Shiwei Li , Xiandi Luo , Haozhao Wang , Xing Tang , Shijie Xu , Weihong Luo , Yuhua Li , Xiuqiang He , Ruixuan Li

Low-rank optimization has emerged as a promising approach to enabling memory-efficient training of large language models (LLMs). Existing low-rank optimization methods typically project gradients onto a low-rank subspace, reducing the…

Machine Learning · Computer Science 2025-12-15 Haochen Zhang , Junze Yin , Guanchu Wang , Zirui Liu , Lin F. Yang , Tianyi Zhang , Anshumali Shrivastava , Vladimir Braverman

Training and fine-tuning large language models (LLMs) come with challenges related to memory and computational requirements due to the increasing size of the model weights and the optimizer states. Various techniques have been developed to…

Machine Learning · Computer Science 2025-12-09 Yehonathan Refael , Jonathan Svirsky , Boris Shustin , Wasim Huleihel , Ofir Lindenbaum