English
Related papers

Related papers: Data Compression using Rank-1 Lattices for Paramet…

200 papers

In lossy compression, Wang et al. [1] recently introduced the rate-distortion-perception-classification function, which supports multi-task learning by jointly optimizing perceptual quality, classification accuracy, and reconstruction…

Information Theory · Computer Science 2025-04-23 Nam Nguyen , Thuan Nguyen , Thinh Nguyen , Bella Bose

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…

Machine Learning · Computer Science 2024-10-07 Rongzhi Zhang , Kuang Wang , Liyuan Liu , Shuohang Wang , Hao Cheng , Chao Zhang , Yelong Shen

Achieving successful variable bitrate compression with computationally simple algorithms from a single end-to-end learned image or video compression model remains a challenge. Many approaches have been proposed, including conditional…

Image and Video Processing · Electrical Eng. & Systems 2024-03-01 Fatih Kamisli , Fabien Racape , Hyomin Choi

We study how much a linear program (LP) can be compressed when solved repeatedly, given prior knowledge about its objective function. Existing data-driven projection methods learn low-dimensional surrogate LPs with approximate…

Optimization and Control · Mathematics 2026-05-26 Yuhan Ye , Omar Bennouna

The Lloyd-Max algorithm is a classical approach to perform K-means clustering. Unfortunately, its cost becomes prohibitive as the training dataset grows large. We propose a compressive version of K-means (CKM), that estimates cluster…

Machine Learning · Computer Science 2017-02-13 Nicolas Keriven , Nicolas Tremblay , Yann Traonmilin , Rémi Gribonval

In this paper, we introduce a novel and robust approach to Quantized Matrix Completion (QMC). First, we propose a rank minimization problem with constraints induced by quantization bounds. Next, we form an unconstrained optimization problem…

Machine Learning · Statistics 2019-02-20 Ashkan Esmaeili , Farokh Marvasti

In high-dimensional multivariate regression problems, enforcing low rank in the coefficient matrix offers effective dimension reduction, which greatly facilitates parameter estimation and model interpretation. However, commonly-used…

Statistics Theory · Mathematics 2017-07-18 Yiyuan She , Kun Chen

Although large language models (LLM) have achieved remarkable performance, their enormous parameter counts hinder deployment on resource-constrained hardware. Low-rank compression can reduce both memory usage and computational demand, but…

Computation and Language · Computer Science 2025-10-13 Yu-Chen Lu , Chong-Yan Chen , Chi-Chih Chang , Yu-Fang Hu , Kai-Chiang Wu

This paper addresses the challenges of storage and communication costs for large-scale datasets in resource-constrained edge devices by proposing a novel dataset quantization approach to reduce intra-sample redundancy. Unlike traditional…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Chenyue Yu , Jianyu Yu

Large Language Models (LLMs) face significant computational challenges when processing long contexts due to the quadratic complexity of self-attention. While soft context compression methods, which map input text to smaller latent…

Computation and Language · Computer Science 2025-09-24 Gabriele Berton , Jayakrishnan Unnikrishnan , Son Tran , Mubarak Shah

A common data analysis task is the reduced-rank regression problem: $$\min_{\textrm{rank-}k \ X} \|AX-B\|,$$ where $A \in \mathbb{R}^{n \times c}$ and $B \in \mathbb{R}^{n \times d}$ are given large matrices and $\|\cdot\|$ is some norm.…

Data Structures and Algorithms · Computer Science 2021-07-02 Praneeth Kacham , David P. Woodruff

Compression techniques for deep neural networks are important for implementing them on small embedded devices. In particular, channel-pruning is a useful technique for realizing compact networks. However, many conventional methods require…

Machine Learning · Statistics 2021-11-03 Kohei Yamamoto , Kurato Maeno

Large language models (LLMs) have recently emerged as powerful tools for tackling many language-processing tasks. Despite their success, training and fine-tuning these models is still far too computationally and memory intensive. In this…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Roy Miles , Pradyumna Reddy , Ismail Elezi , Jiankang Deng

Low Rank Decomposition of matrix - splitting a large matrix into a product of two smaller matrix offers a means for compression that reduces the parameters of a model without sparsification, and hence delivering more speedup on modern…

Computation and Language · Computer Science 2023-09-26 Ayush Kaushal , Tejas Vaidhya , Irina Rish

With increasing size of large language models (LLMs), full-parameter fine-tuning imposes substantial memory demands. To alleviate this, we propose a novel memory-efficient training paradigm called Momentum Low-rank compression (MLorc). The…

Machine Learning · Computer Science 2026-04-28 Wei Shen , Zhang Yaxiang , Minhui Huang , Mengfan Xu , Jiawei Zhang , Cong Shen

Compressing integer keys is a fundamental operation among multiple communities, such as database management (DB), information retrieval (IR), and high-performance computing (HPC). Recent advances in \emph{learned indexes} have inspired the…

Databases · Computer Science 2024-12-17 Qiyu Liu , Siyuan Han , Jianwei Liao , Jin Li , Jingshu Peng , Jun Du , Lei Chen

A key characteristic of deep recommendation models is the immense memory requirements of their embedding tables. These embedding tables can often reach hundreds of gigabytes which increases hardware requirements and training cost. A common…

The estimation of high dimensional precision matrices has been a central topic in statistical learning. However, as the number of parameters scales quadratically with the dimension $p$, many state-of-the-art methods do not scale well to…

Computation · Statistics 2019-07-10 Cheng Wang , Binyan Jiang

The excellent performance of deep neural networks is usually accompanied by a large number of parameters and computations, which have limited their usage on the resource-limited edge devices. To address this issue, abundant methods such as…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Muzhou Yu , Linfeng Zhang , Kaisheng Ma

Rank-1 lattice rules are a class of equally weighted quasi-Monte Carlo methods that achieve essentially linear convergence rates for functions in a reproducing kernel Hilbert space (RKHS) characterized by square-integrable first-order mixed…

Numerical Analysis · Mathematics 2025-06-06 Vesa Kaarnioja , Ilja Klebanov , Claudia Schillings , Yuya Suzuki