paper-with-me

Papers

Accelerating DNN Training with Structured Data Gradient Pruning

2022-02-01 · Bradley McDanel, Helia Dinh, John Magallanes

Weight pruning is a technique to make Deep Neural Network (DNN) inference more computationally efficient by reducing the number of model parameters over the course of training. However, most weight pruning techniques generally does not speed up DNN training and can even require more iterations to reach model convergence. In this work, we propose a novel Structured Data Gradient Pruning (SDGP) method that can speed up training without impacting model convergence. This approach enforces a specific sparsity structure, where only N out of every M elements in a matrix can be nonzero, making it amenable to hardware acceleration. Modern accelerators such as the Nvidia A100 GPU support this type of structured sparsity for 2 nonzeros per 4 elements in a reduction. Assuming hardware support for 2:4 sparsity, our approach can achieve a 15-25\% reduction in total training time without significant impact to performance. Source code and pre-trained models are available at \url{https://github.com/BradMcDanel/sdgp}.

📄 PDF Abstract BibTeX arXiv:2202.00774

Code (1)

bradmcdanel/sdgp 공식 구현 pytorch

Tasks

GPU

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

NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models

2023-10-16 · Jongwoo Ko, Seungjoon Park, Yujin Kim, Sumyeong Ahn 외

Structured pruning methods have proven effective in reducing the model size and accelerating inference speed in various network architectures such as Transformers. Despite the versatility of encoder-decoder models in num…

Decoder

Accelerating CNN Training by Pruning Activation Gradients

2019-08-01 · ECCV 2020 8 · Xucheng Ye, Pengcheng Dai, Junyu Luo, Xin Guo 외

Sparsification is an efficient approach to accelerate CNN inference, but it is challenging to take advantage of sparsity in training procedure because the involved gradients are dynamically changed. Actually, an importan…

Variance-Based Pruning for Accelerating and Compressing Trained Networks

2025-07-17 · Uranik Berisha, Jens Mehnert, Alexandru Paul Condurache arxiv

Increasingly expensive training of ever larger models such as Vision Transfomers motivate reusing the vast library of already trained state-of-the-art networks. However, their latency, high computational costs and memory…

Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

2023-10-10 · Mengzhou Xia, Tianyu Gao, Zhiyuan Zeng, Danqi Chen

The popularity of LLaMA (Touvron et al., 2023a;b) and other recently emerged moderate-sized large language models (LLMs) highlights the potential of building smaller yet powerful LLMs. Regardless, the cost of training su…

Language ModelingLanguage ModellingQuestion AnsweringSentence Completion

A Framework for Neural Network Pruning Using Gibbs Distributions

2020-06-08 · Alex Labach, Shahrokh Valaee

Modern deep neural networks are often too large to use in many practical scenarios. Neural network pruning is an important technique for reducing the size of such models and accelerating inference. Gibbs pruning is a nov…

Network Pruning