English
Related papers

Related papers: Predicting LLM Compression Degradation from Spectr…

200 papers

We introduce compression laws for language language models (LLMs). While recent scaling laws have sought to understand how LLMs scale with respect to model size, pre-training data, and computational resources, we focus on understanding how…

Computation and Language · Computer Science 2025-04-08 Ayan Sengupta , Siddhant Chaudhary , Tanmoy Chakraborty

The components underpinning PLMs -- large weight matrices -- were shown to bear considerable redundancy. Matrix factorization, a well-established technique from matrix theory, has been utilized to reduce the number of parameters in PLM.…

Computation and Language · Computer Science 2023-06-27 Siyu Ren , Kenny Q. Zhu

Data used for analytics and machine learning often take the form of tables with categorical entries. We introduce a family of lossless compression algorithms for such data that proceed in four steps: $(i)$ Estimate latent variables…

Information Theory · Computer Science 2023-02-21 Andrea Montanari , Eric Weiner

In this paper, we tackle the critical challenge of compressing large language models (LLMs) to facilitate their practical deployment and broader adoption. We introduce a novel post-training compression paradigm that focuses on low-rank…

Machine Learning · Computer Science 2025-03-24 Jun Lu , Tianyi Xu , Bill Ding , David Li , Yu Kang

The rapid growth of large language models (LLMs) presents significant deployment challenges due to their massive computational and memory demands. While model compression, such as network pruning, offers potential solutions, most existing…

Machine Learning · Computer Science 2026-04-07 Ziwei Li , Yuang Ma , Yi Kang

Agentic language model (LM) systems power modern applications like "Deep Research" and "Claude Code," and leverage multi-LM architectures to overcome context limitations. Beneath their apparent diversity lies a recurring pattern: smaller…

Machine Learning · Computer Science 2025-12-29 Shizhe He , Avanika Narayan , Ishan S. Khare , Scott W. Linderman , Christopher Ré , Dan Biderman

Current LLM structured pruning methods typically involve two steps: (1) compression with calibration data and (2) costly continued pretraining on billions of tokens to recover lost performance. This second step is necessary as the first…

Machine Learning · Computer Science 2024-12-31 Yaya Sy , Christophe Cerisara , Irina Illina

Deep Click-Through Rate (CTR) prediction models play an important role in modern industrial recommendation scenarios. However, high memory overhead and computational costs limit their deployment in resource-constrained environments.…

Information Retrieval · Computer Science 2024-06-12 Hao Yu , Minghao Fu , Jiandong Ding , Yusheng Zhou , Jianxin Wu

Despite achieving state-of-the-art performance on many NLP tasks, the high energy cost and long inference delay prevent Transformer-based pretrained language models (PLMs) from seeing broader adoption including for edge and mobile…

Computation and Language · Computer Science 2022-11-30 Canwen Xu , Julian McAuley

Deep learning models have achieved tremendous success in most of the industries in recent years. The evolution of these models has also led to an increase in the model size and energy requirement, making it difficult to deploy in production…

Machine Learning · Computer Science 2024-07-24 Aayush Saxena , Arit Kumar Bishwas , Ayush Ashok Mishra , Ryan Armstrong

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

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

We have recently witnessed that ``Intelligence" and `` Compression" are the two sides of the same coin, where the language large model (LLM) with unprecedented intelligence is a general-purpose lossless compressor for various data…

Computer Vision and Pattern Recognition · Computer Science 2024-11-25 Kecheng Chen , Pingping Zhang , Hui Liu , Jie Liu , Yibing Liu , Jiaxin Huang , Shiqi Wang , Hong Yan , Haoliang Li

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Computation and Language · Computer Science 2025-05-12 Jack Merullo , Carsten Eickhoff , Ellie Pavlick

Deep neural networks have achieved state-of-the-art performance across numerous applications, but their high memory and computational demands present significant challenges, particularly in resource-constrained environments. Model…

Machine Learning · Computer Science 2026-02-18 Shihao Zhang , Rayan Saab

Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-rank Adaptation…

Machine Learning · Computer Science 2026-01-29 Longteng Zhang , Sen Wu , Shuai Hou , Zhengyu Qing , Zhuo Zheng , Danning Ke , Qihong Lin , Qiang Wang , Shaohuai Shi , Xiaowen Chu

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language tasks but suffer from extremely large memory footprints and computational costs. In this paper, we introduce a tensor compression…

Machine Learning · Computer Science 2026-01-27 A. El Ichi , K. Jbilou

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

We propose LQ-SGD (Low-Rank Quantized Stochastic Gradient Descent), an efficient communication gradient compression algorithm designed for distributed training. LQ-SGD further develops on the basis of PowerSGD by incorporating the low-rank…

Machine Learning · Computer Science 2025-06-24 Hongyang Li , Lincen Bai , Caesar Wu , Mohammed Chadli , Said Mammar , Pascal Bouvry

Most state of the art deep neural networks are overparameterized and exhibit a high computational cost. A straightforward approach to this problem is to replace convolutional kernels with its low-rank tensor approximations, whereas the…

Computer Vision and Pattern Recognition · Computer Science 2020-08-13 Anh-Huy Phan , Konstantin Sobolev , Konstantin Sozykin , Dmitry Ermilov , Julia Gusak , Petr Tichavsky , Valeriy Glukhov , Ivan Oseledets , Andrzej Cichocki