English
Related papers

Related papers: Rethinking gradient sparsification as total error …

200 papers

Recently, researchers proposed various low-precision gradient compression, for efficient communication in large-scale distributed optimization. Based on these work, we try to reduce the communication complexity from a new direction. We…

Machine Learning · Computer Science 2019-01-25 Jianqiao Wangni , Ke Li , Jianbo Shi , Jitendra Malik

Training Graph Neural Networks (GNNs) on large graphs presents unique challenges due to the large memory and computing requirements. Distributed GNN training, where the graph is partitioned across multiple machines, is a common approach to…

Machine Learning · Computer Science 2024-06-26 Juan Cervino , Md Asadullah Turja , Hesham Mostafa , Nageen Himayat , Alejandro Ribeiro

Large-scale distributed optimization is of great importance in various applications. For data-parallel based distributed learning, the inter-node gradient communication often becomes the performance bottleneck. In this paper, we propose the…

Computer Vision and Pattern Recognition · Computer Science 2018-06-22 Jiaxiang Wu , Weidong Huang , Junzhou Huang , Tong Zhang

We consider the optimization of deep convolutional neural networks (CNNs) such that they provide good performance while having reduced complexity if deployed on either conventional systems utilizing spatial-domain convolution or lower…

Computer Vision and Pattern Recognition · Computer Science 2018-10-30 Yoojin Choi , Mostafa El-Khamy , Jungwon Lee

In the last few years, various communication compression techniques have emerged as an indispensable tool helping to alleviate the communication bottleneck in distributed learning. However, despite the fact biased compressors often show…

Machine Learning · Computer Science 2024-01-17 Aleksandr Beznosikov , Samuel Horváth , Peter Richtárik , Mher Safaryan

Federated learning (FL) enables distributed clients to collaboratively train a machine learning model without sharing raw data with each other. However, it suffers the leakage of private information from uploading models. In addition, as…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-12-25 Kang Wei , Jun Li , Chuan Ma , Ming Ding , Feng Shu , Haitao Zhao , Wen Chen , Hongbo Zhu

With the increasing scale of machine learning tasks, it has become essential to reduce the communication between computing nodes. Early work on gradient compression focused on the bottleneck between CPUs and GPUs, but…

Optimization and Control · Mathematics 2020-06-18 Sarit Khirirat , Sindri Magnússon , Arda Aytekin , Mikael Johansson

We propose a communicationally and computationally efficient algorithm for high-dimensional distributed sparse learning. At each iteration, local machines compute the gradient on local data and the master machine solves one shifted $l_1$…

Machine Learning · Statistics 2017-09-12 Jineng Ren , Jarvis Haupt

We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet. Across thousands…

Machine Learning · Computer Science 2019-02-27 Trevor Gale , Erich Elsen , Sara Hooker

Deep learning model compression is an improving and important field for the edge deployment of deep learning models. Given the increasing size of the models and their corresponding power consumption, it is vital to decrease the model size…

Machine Learning · Computer Science 2022-10-12 Madhumitha Sakthi , Niranjan Yadla , Raj Pawate

Distributed training enables large-scale deep learning, but suffers from high communication overhead, especially as models and datasets grow. Gradient compression, particularly quantization, is a promising approach to mitigate this…

Machine Learning · Computer Science 2025-07-30 Jihao Xin , Marco Canini , Peter Richtárik , Samuel Horváth

Training a sparse neural network from scratch requires optimizing connections at the same time as the weights themselves. Typically, the weights are redistributed after a predefined number of weight updates, removing a fraction of the…

Machine Learning · Computer Science 2022-11-04 Mathias Parger , Alexander Ertl , Paul Eibensteiner , Joerg H. Mueller , Martin Winter , Markus Steinberger

To mitigate communication overheads in distributed model training, several studies propose the use of compressed stochastic gradients, usually achieved by sparsification or quantization. Such techniques achieve high compression ratios, but…

Machine Learning · Computer Science 2021-03-09 Hongyi Wang , Saurabh Agarwal , Dimitris Papailiopoulos

This paper develops a communication-efficient algorithm to solve the stochastic optimization problem defined over a distributed network, aiming at reducing the burdensome communication in applications such as distributed machine…

Machine Learning · Statistics 2020-01-06 Weiyu Li , Tianyi Chen , Liping Li , Zhaoxian Wu , Qing Ling

Deploying deep neural networks (DNNs) on edge devices requires strong compression with minimal accuracy loss. This paper introduces Mix-and-Match Pruning, a globally guided, layer-wise sparsification framework that leverages sensitivity…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Danial Monachan , Samira Nazari , Mahdi Taheri , Ali Azarpeyvand , Milos Krstic , Michael Huebner , Christian Herglotz

This paper addresses two fundamental challenges in distributed online convex optimization: communication efficiency and optimization under limited feedback. We propose a unified framework named Online Compressed Gradient Tracking (OCGT),…

Optimization and Control · Mathematics 2025-12-08 Longkang Zhu , Xinli Shi , Xiangping Xu , Jinde Cao , Xiangyong Chen

The communication of gradients is costly for training deep neural networks with multiple devices in computer vision applications. In particular, the growing size of deep learning models leads to higher communication overheads that defy the…

Machine Learning · Computer Science 2020-02-26 An Xu , Zhouyuan Huo , Heng Huang

Variance reduction methods such as SVRG and SpiderBoost use a mixture of large and small batch gradients to reduce the variance of stochastic gradients. Compared to SGD, these methods require at least double the number of operations per…

Machine Learning · Computer Science 2020-01-28 Melih Elibol , Lihua Lei , Michael I. Jordan

Data-parallel SGD is the de facto algorithm for distributed optimization, especially for large scale machine learning. Despite its merits, communication bottleneck is one of its persistent issues. Most compression schemes to alleviate this…

Neural and Evolutionary Computing · Computer Science 2024-02-07 Ashok Vardhan Makkuva , Marco Bondaschi , Thijs Vogels , Martin Jaggi , Hyeji Kim , Michael C. Gastpar

The communication of gradients is a key bottleneck in distributed training of large scale machine learning models. In order to reduce the communication cost, gradient compression (e.g., sparsification and quantization) and error…

Optimization and Control · Mathematics 2021-09-22 Xun Qian , Hanze Dong , Peter Richtárik , Tong Zhang