English
Related papers

Related papers: ABS: Adaptive Bounded Staleness Converges Faster a…

200 papers

The increasing size of deep learning models has made distributed training across multiple devices essential. However, current methods such as distributed data-parallel training suffer from large communication and synchronization overheads…

Machine Learning · Computer Science 2025-02-10 Cabrel Teguemne Fokam , Khaleelulla Khan Nazeer , Lukas König , David Kappel , Anand Subramoney

Consensus is one of the fundamental tasks studied in distributed computing. Processors have input values from some set $V$ and they have to decide the same value from this set. If all processors have the same input value, then they must all…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-08-27 Kokouvi Hounkanli , Avery Miller , Andrzej Pelc

Deep neural networks have been shown to achieve state-of-the-art performance in several machine learning tasks. Stochastic Gradient Descent (SGD) is the preferred optimization algorithm for training these networks and asynchronous SGD…

Machine Learning · Computer Science 2016-04-06 Wei Zhang , Suyog Gupta , Xiangru Lian , Ji Liu

We study the problem of stochastic optimization for deep learning in the parallel computing environment under communication constraints. A new algorithm is proposed in this setting where the communication and coordination of work among…

Machine Learning · Computer Science 2015-10-27 Sixin Zhang , Anna Choromanska , Yann LeCun

Asynchronous computation and gradient compression have emerged as two key techniques for achieving scalability in distributed optimization for large-scale machine learning. This paper presents a unified analysis framework for distributed…

Optimization and Control · Mathematics 2018-11-30 Sarit Khirirat , Hamid Reza Feyzmahdavian , Mikael Johansson

In this paper, we study asynchronous federated learning (FL) in a wireless distributed learning network (WDLN). To allow each edge device to use its local data more efficiently via asynchronous FL, transmission scheduling in the WDLN for…

Information Theory · Computer Science 2021-08-31 Hyun-Suk Lee , Jang-Won Lee

We consider stochastic optimization with delayed gradients where, at each time step $t$, the algorithm makes an update using a stale stochastic gradient from step $t - d_t$ for some arbitrary delay $d_t$. This setting abstracts asynchronous…

Optimization and Control · Mathematics 2021-11-16 Alon Cohen , Amit Daniely , Yoel Drori , Tomer Koren , Mariano Schain

Wireless networking is becoming an increasingly important and popular way of providing global information access to users on the move. One of the main challenges for seamless mobility is the availability of simple and robust handoff…

Networking and Internet Architecture · Computer Science 2012-06-18 Siva Alagu , T. Meyyappan

Bulk synchronous parallel (BSP) is the de-facto paradigm for distributed DNN training in today's production clusters. However, due to the global synchronization nature, its performance can be significantly influenced by network bottlenecks…

Machine Learning · Computer Science 2022-01-14 Weiyan Wang , Cengguang Zhang , Liu Yang , Kai Chen , Kun Tan

While distributed training significantly speeds up the training process of the deep neural network (DNN), the utilization of the cluster is relatively low due to the time-consuming data synchronizing between workers. To alleviate this…

Machine Learning · Computer Science 2020-12-01 Yuhao Zhou , Qing Ye , Hailun Zhang , Jiancheng Lv

Decentralized optimization has emerged as a critical paradigm for distributed learning, enabling scalable training while preserving data privacy through peer-to-peer collaboration. However, existing methods often suffer from communication…

Machine Learning · Computer Science 2026-01-06 Yijie Zhou , Shi Pu

Significant progress has been made in the area of model-based reinforcement learning. State-of-the-art algorithms are now able to match the asymptotic performance of model-free methods while being significantly more data efficient. However,…

Machine Learning · Computer Science 2019-10-29 Yunzhi Zhang , Ignasi Clavera , Boren Tsai , Pieter Abbeel

Distributed stateful stream processing enables the deployment and execution of large scale continuous computations in the cloud, targeting both low latency and high throughput. One of the most fundamental challenges of this paradigm is…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-06-30 Paris Carbone , Gyula Fóra , Stephan Ewen , Seif Haridi , Kostas Tzoumas

We consider the distributed learning problem with data dispersed across multiple workers under the orchestration of a central server. Asynchronous Stochastic Gradient Descent (SGD) has been widely explored in such a setting to reduce the…

Machine Learning · Computer Science 2024-05-28 Xiaolu Wang , Yuchang Sun , Hoi-To Wai , Jun Zhang

Although distributed computing can significantly reduce the training time of deep neural networks, scaling the training process while maintaining high efficiency and final accuracy is challenging. Distributed asynchronous training enjoys…

Machine Learning · Computer Science 2020-10-15 Ido Hakimi , Saar Barkai , Moshe Gabel , Assaf Schuster

Consensus-based distributed optimization methods have recently been advocated as alternatives to parameter server and ring all-reduce paradigms for large scale training of machine learning models. In this case, each worker maintains a local…

Machine Learning · Computer Science 2020-03-02 Giovanni Neglia , Chuan Xu , Don Towsley , Gianmarco Calbi

We consider the setting where a master wants to run a distributed stochastic gradient descent (SGD) algorithm on $n$ workers each having a subset of the data. Distributed SGD may suffer from the effect of stragglers, i.e., slow or…

Machine Learning · Computer Science 2023-10-18 Serge Kas Hanna , Rawad Bitar , Parimal Parag , Venkat Dasari , Salim El Rouayheb

Communication bottlenecks severely hinder the scalability of distributed neural network training, particularly in high-performance computing (HPC) environments. We introduce AB-training, a novel data-parallel method that leverages low-rank…

This paper studies the robustness of a dynamic average consensus algorithm to communication delay over strongly connected and weight-balanced (SCWB) digraphs. Under delay-free communication, the algorithm of interest achieves a practical…

Systems and Control · Computer Science 2018-12-12 Hossein Moradian , Solmaz S. Kia

In decentralized optimization, nodes of a communication network each possess a local objective function, and communicate using gossip-based methods in order to minimize the average of these per-node functions. While synchronous algorithms…

Optimization and Control · Mathematics 2022-09-02 Mathieu Even , Hadrien Hendrikx , Laurent Massoulie
‹ Prev 1 4 5 6 7 8 10 Next ›