English
Related papers

Related papers: Double Quantization for Communication-Efficient Di…

200 papers

Many communication-efficient variants of SGD use gradient quantization schemes. These schemes are often heuristic and fixed over the course of training. We empirically observe that the statistics of gradients of deep models change during…

Machine Learning · Computer Science 2020-10-26 Fartash Faghri , Iman Tabrizian , Ilia Markov , Dan Alistarh , Daniel Roy , Ali Ramezani-Kebrya

Distributed deep learning (DL) has become prevalent in recent years to reduce training time by leveraging multiple computing devices (e.g., GPUs/TPUs) due to larger models and datasets. However, system scalability is limited by…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-09-04 Zhenheng Tang , Shaohuai Shi , Wei Wang , Bo Li , Xiaowen Chu

Gradient quantization is an emerging technique in reducing communication costs in distributed learning. Existing gradient quantization algorithms often rely on engineering heuristics or empirical observations, lacking a systematic approach…

Machine Learning · Computer Science 2021-08-02 Guangfeng Yan , Shao-Lun Huang , Tian Lan , Linqi Song

A standard approach in large scale machine learning is distributed stochastic gradient training, which requires the computation of aggregated stochastic gradients over multiple nodes on a network. Communication is a major bottleneck in such…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-03-24 Hanlin Tang , Xiangru Lian , Chen Yu , Tong Zhang , Ji Liu

Communication of model updates between client nodes and the central aggregating server is a major bottleneck in federated learning, especially in bandwidth-limited settings and high-dimensional models. Gradient quantization is an effective…

Machine Learning · Computer Science 2021-02-10 Divyansh Jhunjhunwala , Advait Gadhikar , Gauri Joshi , Yonina C. Eldar

In distributed training, the communication cost due to the transmission of gradients or the parameters of the deep model is a major bottleneck in scaling up the number of processing nodes. To address this issue, we propose \emph{dithered…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-04-03 Afshin Abdi , Faramarz Fekri

Due to its efficiency and ease to implement, stochastic gradient descent (SGD) has been widely used in machine learning. In particular, SGD is one of the most popular optimization methods for distributed learning. Recently, quantized SGD…

Machine Learning · Computer Science 2019-01-11 Shen-Yi Zhao , Hao Gao , Wu-Jun Li

Federated Learning (FL) enables participant devices to collaboratively train deep learning models without sharing their data with the server or other devices, effectively addressing data privacy and computational concerns. However, FL faces…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Asadullah Tariq , Tariq Qayyum , Mohamed Adel Serhani , Farag Sallabi , Ikbal Taleb , Ezedin S. Barka

Communication bottleneck has been identified as a significant issue in distributed optimization of large-scale learning models. Recently, several approaches to mitigate this problem have been proposed, including different forms of gradient…

Machine Learning · Statistics 2019-11-05 Debraj Basu , Deepesh Data , Can Karakus , Suhas Diggavi

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

Next-generation wireless networks, such as edge intelligence and wireless distributed learning, face two critical challenges: communication efficiency and privacy protection. In this work, our focus is on addressing these issues in a…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-12-13 Guangfeng Yan , Tan Li , Tian Lan , Kui Wu , Linqi Song

As the size and complexity of models and datasets grow, so does the need for communication-efficient variants of stochastic gradient descent that can be deployed to perform parallel model training. One popular communication-compression…

Machine Learning · Computer Science 2021-05-05 Ali Ramezani-Kebrya , Fartash Faghri , Ilya Markov , Vitalii Aksenov , Dan Alistarh , Daniel M. Roy

As the size and complexity of models and datasets grow, so does the need for communication-efficient variants of stochastic gradient descent that can be deployed to perform parallel model training. One popular communication-compression…

Machine Learning · Computer Science 2021-05-24 Ali Ramezani-Kebrya , Fartash Faghri , Ilya Markov , Vitalii Aksenov , Dan Alistarh , Daniel M. Roy

Increasing the number of parameters in large language models (LLMs) usually improves performance in downstream tasks but raises compute and memory costs, making deployment difficult in resource-limited settings. Quantization techniques,…

Computation and Language · Computer Science 2024-06-07 Renren Jin , Jiangcun Du , Wuwei Huang , Wei Liu , Jian Luan , Bin Wang , Deyi Xiong

Large-scale machine learning models are often trained by parallel stochastic gradient descent algorithms. However, the communication cost of gradient aggregation and model synchronization between the master and worker nodes becomes the…

Machine Learning · Computer Science 2020-07-03 Xiaorui Liu , Yao Li , Jiliang Tang , Ming Yan

In modern large-scale machine learning applications, the training data are often partitioned and stored on multiple machines. It is customary to employ the "data parallelism" approach, where the aggregated training loss is minimized without…

Machine Learning · Computer Science 2017-08-28 Shun Zheng , Jialei Wang , Fen Xia , Wei Xu , Tong Zhang

Many popular distributed optimization methods for training machine learning models fit the following template: a local gradient estimate is computed independently by each worker, then communicated to a master, which subsequently performs…

Machine Learning · Computer Science 2019-06-05 Konstantin Mishchenko , Filip Hanzely , Peter Richtárik

Distributed model training suffers from communication overheads due to frequent gradient updates transmitted between compute nodes. To mitigate these overheads, several studies propose the use of sparsified stochastic gradients. We argue…

The present paper develops a novel aggregated gradient approach for distributed machine learning that adaptively compresses the gradient communication. The key idea is to first quantize the computed gradients, and then skip less informative…

Machine Learning · Computer Science 2019-09-18 Jun Sun , Tianyi Chen , Georgios B. Giannakis , Zaiyue Yang

We propose a communication-efficient optimally structured gradient coding scheme to jointly address straggler resilience and communication efficiency in heterogeneous distributed learning. By establishing a unified framework that…

Systems and Control · Electrical Eng. & Systems 2026-05-18 Heekang Song , Wan Choi