English
Related papers

Related papers: DeMo: Decoupled Momentum Optimization

200 papers

Decentralized optimization is emerging as a viable alternative for scalable distributed machine learning, but also introduces new challenges in terms of synchronization costs. To this end, several communication-reduction techniques, such as…

Machine Learning · Computer Science 2022-03-28 Giorgi Nadiradze , Amirmojtaba Sabour , Peter Davies , Shigang Li , Dan Alistarh

Recent developments on large-scale distributed machine learning applications, e.g., deep neural networks, benefit enormously from the advances in distributed non-convex optimization techniques, e.g., distributed Stochastic Gradient Descent…

Optimization and Control · Mathematics 2019-05-13 Hao Yu , Rong Jin , Sen Yang

We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator. We propose to train personalized models…

Machine Learning · Computer Science 2024-12-20 Valentina Zantedeschi , Aurélien Bellet , Marc Tommasi

In this work, we study decentralized stochastic nonconvex Polyak--{\L}ojasiewicz minimax problems and propose a communication-efficient algorithm. Motivated by the efficiency of local SGD in federated learning, we investigate decentralized…

Optimization and Control · Mathematics 2026-05-26 Haoyuan Cai , Sulaiman A. Alghunaim , Ali H. Sayed

Big data, including applications with high security requirements, are often collected and stored on multiple heterogeneous devices, such as mobile devices, drones and vehicles. Due to the limitations of communication costs and security…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-10-05 Hao Chen , Yu Ye , Ming Xiao , Mikael Skoglund , H. Vincent Poor

We introduce $\mathbf{G}$radient Descent with $\mathbf{A}$daptive $\mathbf{M}$omentum $\mathbf{S}$caling ($\mathbf{Grams}$), a novel optimization algorithm that decouples the direction and magnitude of parameter updates in deep learning.…

Machine Learning · Computer Science 2025-03-06 Yang Cao , Xiaoyu Li , Zhao Song

Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks, as well as for efficient scaling to large compute clusters. As current approaches suffer from limited bandwidth…

Machine Learning · Computer Science 2020-11-12 Anastasia Koloskova , Tao Lin , Sebastian U. Stich , Martin Jaggi

In this work, we consider the integration of MPI one-sided communication and non-blocking I/O in HPC-centric MapReduce frameworks. Using a decoupled strategy, we aim to overlap the Map and Reduce phases of the algorithm by allowing…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-10-10 Sergio Rivas-Gomez , Sai Narasimhamurthy , Keeran Brabazon , Oliver Perks , Erwin Laure , Stefano Markidis

Modern mobile devices have access to a wealth of data suitable for learning models, which in turn can greatly improve the user experience on the device. For example, language models can improve speech recognition and text entry, and image…

Machine Learning · Computer Science 2023-01-30 H. Brendan McMahan , Eider Moore , Daniel Ramage , Seth Hampson , Blaise Agüera y Arcas

Large-scale machine learning training, in particular distributed stochastic gradient descent, needs to be robust to inherent system variability such as node straggling and random communication delays. This work considers a distributed…

Machine Learning · Computer Science 2019-03-08 Jianyu Wang , Gauri Joshi

Decentralized SGD can run with low communication costs, but its sparse communication characteristics deteriorate the convergence rate, especially when the number of nodes is large. In decentralized learning settings, communication is…

Machine Learning · Computer Science 2025-03-03 Yuki Takezawa , Sebastian U. Stich

In this paper, we consider hybrid parallelism -- a paradigm that employs both Data Parallelism (DP) and Model Parallelism (MP) -- to scale distributed training of large recommendation models. We propose a compression framework called…

Edge computing provides resources for IoT workloads at the network edge. Monitoring systems are vital for efficiently managing resources and application workloads by collecting, storing, and providing relevant information about the state of…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-14 Shashikant Ilager , Jakob Fahringer , Alessandro Tundo , Ivona Brandić

Distributed synchronous stochastic gradient descent has been widely used to train deep neural networks (DNNs) on computer clusters. With the increase of computational power, network communications generally limit the system scalability.…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-01-19 Shaohuai Shi , Xiaowen Chu , Bo Li

Emerging applications in multi-agent environments such as internet-of-things, networked sensing, autonomous systems and federated learning, call for decentralized algorithms for finite-sum optimizations that are resource-efficient in terms…

Machine Learning · Statistics 2021-12-03 Boyue Li , Zhize Li , Yuejie Chi

Efficient stochastic optimization typically integrates an update direction that performs well in the deterministic regime with a mechanism adapting to stochastic perturbations. While Adam uses adaptive moment estimates to promote stability,…

Machine Learning · Computer Science 2026-02-23 Minxin Zhang , Yuxuan Liu , Hayden Schaeffer

In modern decentralized applications, ensuring communication efficiency and privacy for the users are the key challenges. In order to train machine-learning models, the algorithm has to communicate to the data center and sample data for its…

Optimization and Control · Mathematics 2024-04-04 Hoang Huy Nguyen , Yan Li , Tuo Zhao

Gradient orthogonalization is a simple strategy that shows great utility in speeding up gradient descent. The Muon optimizer (Jordan, Jin, et al., 2024) combines gradient orthogonalization with first-order momentum and achieves significant…

Machine Learning · Computer Science 2025-10-21 Ahmed Khaled , Kaan Ozkara , Tao Yu , Mingyi Hong , Youngsuk Park

Recent multimodal systems often rely on separate expert modality encoders which cause linearly scaling complexity and computational overhead with added modalities. While unified Omni-models address this via Mixture-of-Expert (MoE)…

Multimedia · Computer Science 2026-03-09 Kin Wai Lau , Yasar Abbas Ur Rehman , Lai-Man Po , Pedro Porto Buarque de Gusmão

We present a new class of decentralized first-order methods for nonsmooth and stochastic optimization problems defined over multiagent networks. Considering that communication is a major bottleneck in decentralized optimization, our main…

Optimization and Control · Mathematics 2017-02-07 Guanghui Lan , Soomin Lee , Yi Zhou