English
Related papers

Related papers: LoSparse: Structured Compression of Large Language…

200 papers

Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads) while maintaining…

Machine Learning · Computer Science 2024-06-25 Bo-Kyeong Kim , Geonmin Kim , Tae-Ho Kim , Thibault Castells , Shinkook Choi , Junho Shin , Hyoung-Kyu Song

We propose a neural language modeling system based on low-rank adaptation (LoRA) for speech recognition output rescoring. Although pretrained language models (LMs) like BERT have shown superior performance in second-pass rescoring, the high…

Memory constraint of always-on devices is one of the major concerns when deploying speech processing models on these devices. While larger models trained with sufficiently large amount of data generally perform better, making them fit in…

Computation and Language · Computer Science 2024-01-09 Yiming Wang , Jinyu Li

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

The goal of model compression is to reduce the size of a large neural network while retaining a comparable performance. As a result, computation and memory costs in resource-limited applications may be significantly reduced by dropping…

Machine Learning · Statistics 2022-11-10 Wenjing Yang , Ganghua Wang , Jie Ding , Yuhong Yang

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

Iterative pruning is one of the most effective compression methods for pre-trained language models. We discovered that finding the optimal pruning decision is an equality-constrained 0-1 Integer Linear Programming problem. The solution to…

Computation and Language · Computer Science 2023-05-23 Siyu Ren , Kenny Q. Zhu

Pruning the weights of neural networks is an effective and widely-used technique for reducing model size and inference complexity. We develop and test a novel method based on compressed sensing which combines the pruning and training into a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-08 Jonathan W. Siegel , Jianhong Chen , Pengchuan Zhang , Jinchao Xu

Large Language Models (LLMs) have made significant strides in natural language processing and generation, yet their ability to handle long-context input remains constrained by the quadratic complexity of attention computation and…

Computation and Language · Computer Science 2025-06-16 Manlai Liang , Wanyi Huang , Mandi Liu , Huaijun Li , Jinlong Li

While Convolutional Neural Networks (CNNs) excel at learning complex latent-space representations, their over-parameterization can lead to overfitting and reduced performance, particularly with limited data. This, alongside their high…

Computer Vision and Pattern Recognition · Computer Science 2024-01-17 Manish Sharma , Jamison Heard , Eli Saber , Panos P. Markopoulos

Compression has emerged as one of the essential deep learning research topics, especially for the edge devices that have limited computation power and storage capacity. Among the main compression techniques, low-rank compression via matrix…

Machine Learning · Computer Science 2021-12-02 Moonjung Eo , Suhyun Kang , Wonjong Rhee

Imposing an effective structural assumption on neural network weight matrices has been the major paradigm for designing Parameter-Efficient Fine-Tuning (PEFT) systems for adapting modern large pre-trained models to various downstream tasks.…

Machine Learning · Computer Science 2025-02-20 Xin Li , Anand Sarwate

We introduce and compare new compression approaches to obtain regularized solutions of large linear systems which are commonly encountered in large scale inverse problems. We first describe how to approximate matrix vector operations with a…

Numerical Analysis · Mathematics 2016-08-12 Sergey Voronin , Dylan Mikesell , Guust Nolet

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

We propose TLoRA, a novel tri-matrix low-rank adaptation method that decomposes weight updates into three matrices: two fixed random matrices and one trainable matrix, combined with a learnable, layer-wise scaling factor. This tri-matrix…

Machine Learning · Computer Science 2025-12-02 Tanvir Islam

Fine-tuning pre-trained large language models in a parameter-efficient manner is widely studied for its effectiveness and efficiency. The popular method of low-rank adaptation (LoRA) offers a notable approach, hypothesizing that the…

Computation and Language · Computer Science 2023-11-21 Ning Ding , Xingtai Lv , Qiaosen Wang , Yulin Chen , Bowen Zhou , Zhiyuan Liu , Maosong Sun

A central goal of neuroscience is to understand how activity in the nervous system is related to features of the external world, or to features of the nervous system itself. A common approach is to model neural responses as a weighted…

Machine Learning · Statistics 2015-05-14 Kristofer E. Bouchard

Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…

Computation and Language · Computer Science 2026-04-17 Andrew Kiruluta

Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that…

Adapting large-scale pretrained language models to downstream tasks via fine-tuning is the standard method for achieving state-of-the-art performance on NLP benchmarks. However, fine-tuning all weights of models with millions or billions of…

Computation and Language · Computer Science 2021-11-30 Rabeeh Karimi Mahabadi , James Henderson , Sebastian Ruder
‹ Prev 1 4 5 6 7 8 10 Next ›