English
Related papers

Related papers: Language model compression with weighted low-rank …

200 papers

The prohibitive sizes of Large Language Models (LLMs) today make it difficult to deploy them on memory-constrained edge devices. This work introduces $\rm CALDERA$ -- a new post-training LLM compression algorithm that harnesses the inherent…

Machine Learning · Computer Science 2024-11-05 Rajarshi Saha , Naomi Sagan , Varun Srivastava , Andrea J. Goldsmith , Mert Pilanci

Self-supervised speech representation learning (SSL) has shown to be effective in various downstream tasks, but SSL models are usually large and slow. Model compression techniques such as pruning aim to reduce the model size and computation…

Computation and Language · Computer Science 2023-03-01 Yifan Peng , Kwangyoun Kim , Felix Wu , Prashant Sridhar , Shinji Watanabe

This paper is devoted to proposing a general weighted low-rank recovery model and designing a fast SVD-free computational scheme to solve it. First, our generic weighted low-rank recovery model unifies several existing approaches in the…

Optimization and Control · Mathematics 2022-08-02 Aritra Dutta , Jingwei Liang , Xin Li

Low-rank approximations, of the weight and feature space can enhance the performance of deep learning models, whether in terms of improving generalization or reducing the latency of inference. However, there is no clear consensus yet on…

Computation and Language · Computer Science 2024-05-24 Arnav Chavan , Nahush Lele , Deepak Gupta

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

Aiming to provide a faster and convenient truncated SVD algorithm for large sparse matrices from real applications (i.e. for computing a few of largest singular values and the corresponding singular vectors), a dynamically shifted power…

Mathematical Software · Computer Science 2024-04-16 Xu Feng , Wenjian Yu , Yuyang Xie , Jie Tang

Achieving efficient and robust multi-channel data learning is a challenging task in data science. By exploiting low-rankness in the transformed domain, i.e., transformed low-rankness, tensor Singular Value Decomposition (t-SVD) has achieved…

Machine Learning · Computer Science 2023-12-21 Andong Wang , Chao Li , Mingyuan Bai , Zhong Jin , Guoxu Zhou , Qibin Zhao

Popular PEFT methods reduce trainable parameter count for fine-tuning by parameterizing new low-rank or sparse trainable weights in parallel to the frozen pre-trained weights $W$. However, these weights are trained from scratch, and there…

Machine Learning · Computer Science 2025-08-15 Suhas G Hegde , Shilpy Kaur , Aruna Tiwari

Due to the iterative nature of most nonnegative matrix factorization (\textsc{NMF}) algorithms, initialization is a key aspect as it significantly influences both the convergence and the final solution obtained. Many initialization schemes…

Numerical Analysis · Computer Science 2019-02-25 Atif Muhammad Syed , Sameer Qazi , Nicolas Gillis

Return panels, covariances, and large feature matrices evolve one observation or one entry at a time, yet downstream models require an up-to-date low-rank factorization $A_t \approx U_t \Sigma_t V_t^\top$ on every tick -- a regime where…

Numerical Analysis · Mathematics 2026-05-26 Stilyan Staykov

Large-scale foundation models have demonstrated remarkable versatility across a wide range of downstream tasks. However, fully fine-tuning these models incurs prohibitive computational costs, motivating the development of…

Machine Learning · Computer Science 2025-05-30 Chongjie Si , Xuankun Yang , Muqing Liu , Yadao Wang , Xiaokang Yang , Wenbo Su , Bo Zheng , Wei Shen

Reducing parameter redundancies in neural network architectures is crucial for achieving feasible computational and memory requirements during training and inference phases. Given its easy implementation and flexibility, one promising…

Machine Learning · Computer Science 2025-08-22 Emanuele Zangrando , Steffen Schotthöfer , Gianluca Ceruti , Jonas Kusch , Francesco Tudisco

Freezing the pre-trained backbone has become a standard paradigm to avoid overfitting in few-shot segmentation. In this paper, we rethink the paradigm and explore a new regime: {\em fine-tuning a small part of parameters in the backbone}.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Yanpeng Sun , Qiang Chen , Xiangyu He , Jian Wang , Haocheng Feng , Junyu Han , Errui Ding , Jian Cheng , Zechao Li , Jingdong Wang

Compressed sensing of simultaneously sparse and low-rank matrices enables recovery of sparse signals from a few linear measurements of their bilinear form. One important question is how many measurements are needed for a stable…

Information Theory · Computer Science 2016-07-01 Kiryung Lee , Yihong Wu , Yoram Bresler

This paper proposes a novel, efficient transfer learning method, called Scalable Weight Reparametrization (SWR) that is efficient and effective for multiple downstream tasks. Efficient transfer learning involves utilizing a pre-trained…

Machine Learning · Computer Science 2023-02-28 Byeonggeun Kim , Jun-Tae Lee , Seunghan yang , Simyung Chang

In this paper, we introduce a novel method of neural network weight compression. In our method, we store weight tensors as sparse, quantized matrix factors, whose product is computed on the fly during inference to generate the target…

Machine Learning · Computer Science 2022-07-25 Andrey Kuzmin , Mart van Baalen , Markus Nagel , Arash Behboodi

Convolutional neural networks (CNNs) have long been the paradigm of choice for robust medical image processing (MIP). Therefore, it is crucial to effectively and efficiently deploy CNNs on devices with different computing capabilities to…

Computer Vision and Pattern Recognition · Computer Science 2024-03-04 Zexin Feng , Na Zeng , Jiansheng Fang , Xingyue Wang , Xiaoxi Lu , Heng Meng , Jiang Liu

Sparsity regularization has garnered significant interest across multiple disciplines, including statistics, imaging, and signal processing. Standard techniques for addressing sparsity regularization include iterative soft thresholding…

Optimization and Control · Mathematics 2025-06-16 Long Li , Liang Ding

This article studies the problem of decentralized Singular Value Decomposition (d-SVD), which is fundamental in various signal processing applications. Two scenarios are considered depending on the availability of the data matrix under…

Signal Processing · Electrical Eng. & Systems 2025-01-10 Yufan Fan , Marius Pesavento

Multilingual language model (LM) have become a powerful tool in NLP especially for non-English languages. Nevertheless, model parameters of multilingual LMs remain large due to the larger embedding matrix of the vocabulary covering tokens…

Computation and Language · Computer Science 2023-10-20 Asahi Ushio , Yi Zhou , Jose Camacho-Collados