paper-with-me

Papers

Structured Deep Neural Network Pruning via Matrix Pivoting

2017-12-01 · Ranko Sredojevic, Shaoyi Cheng, Lazar Supic, Rawan Naous, Vladimir Stojanovic

Deep Neural Networks (DNNs) are the key to the state-of-the-art machine vision, sensor fusion and audio/video signal processing. Unfortunately, their computation complexity and tight resource constraints on the Edge make them hard to leverage on mobile, embedded and IoT devices. Due to great diversity of Edge devices, DNN designers have to take into account the hardware platform and application requirements during network training. In this work we introduce pruning via matrix pivoting as a way to improve network pruning by compromising between the design flexibility of architecture-oblivious and performance efficiency of architecture-aware pruning, the two dominant techniques for obtaining resource-efficient DNNs. We also describe local and global network optimization techniques for efficient implementation of the resulting pruned networks. In combination, the proposed pruning and implementation result in close to linear speed up with the reduction of network coefficients during pruning.

📄 PDF Abstract BibTeX arXiv:1712.01084

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityNetwork PruningSensor Fusion

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models

2025-01-31 · Jialin Zhao, Yingtao Zhang, Carlo Vittorio Cannistraci

The rapid growth of Large Language Models has driven demand for effective model compression techniques to reduce memory and computation costs. Low-rank pruning has gained attention for its tensor coherence and GPU compat…

GPUModel Compression

Tight Compression: Compressing CNN Through Fine-Grained Pruning and Weight Permutation for Efficient Implementation

2021-04-03 · Xizi Chen, Jingyang Zhu, Jingbo Jiang, Chi-Ying Tsui

The unstructured sparsity after pruning poses a challenge to the efficient implementation of deep learning models in existing regular architectures like systolic arrays. On the other hand, coarse-grained structured pruni…

Model Compression

Towards Perturbation-Induced Static Pivoting on GPU-Based Linear Solvers

2023-11-20 · Samuel Chevalier, Robert Parker

Linear system solving is a key tool for computational power system studies, e.g., optimal power flow, transmission switching, or unit commitment. CPU-based linear system solver speeds, however, have saturated in recent y…

CPUGPU

Learnable Permutation for Structured Sparsity on Transformer Models

2026-01-30 · Zekai Li, Ji Liu, Guanchen Li, Yixing Xu 외 arxiv

Structured sparsity has emerged as a popular model pruning technique, widely adopted in various architectures, including CNNs, Transformer models, and especially large language models (LLMs) in recent years. A promising …

Structured Pruning of Large Language Models

2019-10-10 · EMNLP 2020 11 · Ziheng Wang, Jeremy Wohlwend, Tao Lei

Large language models have recently achieved state of the art performance across a wide variety of natural language tasks. Meanwhile, the size of these models and their latency have significantly increased, which makes t…

Language ModelingLanguage ModellingModel CompressionWord Embeddings