paper-with-me

Papers

Efficient Decentralized Deep Learning by Dynamic Model Averaging

2018-07-09 · Michael Kamp, Linara Adilova, Joachim Sicking, Fabian Hüger, Peter Schlicht, Tim Wirtz, Stefan Wrobel

We propose an efficient protocol for decentralized training of deep neural networks from distributed data sources. The proposed protocol allows to handle different phases of model training equally well and to quickly adapt to concept drifts. This leads to a reduction of communication by an order of magnitude compared to periodically communicating state-of-the-art approaches. Moreover, we derive a communication bound that scales well with the hardness of the serialized learning problem. The reduction in communication comes at almost no cost, as the predictive performance remains virtually unchanged. Indeed, the proposed protocol retains loss bounds of periodically averaging schemes. An extensive empirical evaluation validates major improvement of the trade-off between model performance and communication which could be beneficial for numerous decentralized learning applications, such as autonomous driving, or voice recognition and image classification on mobile phones.

📄 PDF Abstract BibTeX arXiv:1807.03210

Code (1)

fraunhofer-iais/dlplatform/tree/master/DLplatform 공식 구현

Tasks

Autonomous DrivingDeep LearningGeneral Classificationimage-classificationImage Classificationmodel

Similar Papers 제목 키워드 기반

Coordinate Dual Averaging for Decentralized Online Optimization with Nonseparable Global Objectives

2015-08-31 · Soomin Lee, Angelia Nedić, Maxim Raginsky

We consider a decentralized online convex optimization problem in a network of agents, where each agent controls only a coordinate (or a part) of the global decision vector. For such a problem, we propose two decentraliz…

Exponential Graph is Provably Efficient for Decentralized Deep Training

2021-10-26 · NeurIPS 2021 12 · Bicheng Ying, Kun Yuan, Yiming Chen, Hanbin Hu 외

Decentralized SGD is an emerging training method for deep learning known for its much less (thus faster) communication per iteration, which relaxes the averaging step in parallel SGD to inexact averaging. The less exact …

Averaging Rate Scheduler for Decentralized Learning on Heterogeneous Data

2024-03-05 · Sai Aparna Aketi, Sakshi Choudhary, Kaushik Roy

State-of-the-art decentralized learning algorithms typically require the data distribution to be Independent and Identically Distributed (IID). However, in practical scenarios, the data distribution across the agents can…

Scheduling

Rapid Grassmannian Averaging with Chebyshev Polynomials

2024-10-11 · Brighton Ancelin, Alex Saad-Falcon, Kason Ancelin, Justin Romberg

We propose new algorithms to efficiently average a collection of points on a Grassmannian manifold in both the centralized and decentralized settings. Grassmannian points are used ubiquitously in machine learning, comput…

Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization

2018-06-03 · NeurIPS 2018 12 · Hoi-To Wai, Zhuoran Yang, Zhaoran Wang, Mingyi Hong

Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents. Motivated by decentralized applications such as sensor…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)