Adversary-Resilient Distributed and Decentralized Statistical Inference and Machine Learning: An Overview of Recent Advances Under the Byzantine Threat Model

Yang Zhixiong; Gang Arpita; Bajwa Waheed U.

首页> 外文期刊>IEEE Signal Processing Magazine >Adversary-Resilient Distributed and Decentralized Statistical Inference and Machine Learning: An Overview of Recent Advances Under the Byzantine Threat Model

【24h】

Adversary-Resilient Distributed and Decentralized Statistical Inference and Machine Learning: An Overview of Recent Advances Under the Byzantine Threat Model

机译：逆境 - 弹性分布式和分散统计推理和机器学习：拜占庭威胁模型下最近进步的概述

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Statistical inference and machine-learning algorithms have traditionally been developed for data available at a single location. Unlike this centralized setting, modern data sets are increasingly being distributed across multiple physical entities (sensors, devices, machines, data centers, and so on) for a multitude of reasons that range from storage, memory, and computational constraints to privacy concerns and engineering needs. This has necessitated the development of inference and learning algorithms capable of operating on noncolocated data. For this article, we divide such algorithms into two broad categories, namely, distributed algorithms and decentralized algorithms (see "Is It Distributed or Is It Decentralized?").

机译：传统上，统计推断和机器学习算法是为单个位置提供的数据开发的。与这种集中式设置不同，现代数据集越来越多地分布在多种物理实体（传感器，设备，机器，数据中心等）上分发，以实现从存储，内存和计算限制到隐私问题和工程的多种原因需要。这需要开发能够在非分解数据上运行的推理和学习算法。对于本文，我们将这种算法划分为两个广泛的类别，即分布式算法和分散的算法（参见“它是分布的或它分散？”）。

著录项

来源
《IEEE Signal Processing Magazine》 |2020年第3期|146-159|共14页
作者
Yang Zhixiong; Gang Arpita; Bajwa Waheed U.;
展开▼
作者单位

Blue Danube Syst Santa Clara CA 95054 USA;

Rutgers State Univ Elect Engn New Brunswick NJ USA;

Rutgers State Univ Dept Elect & Comp Engn New Brunswick NJ USA|Rutgers State Univ Dept Stat New Brunswick NJ USA;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词

相似文献

外文文献
专利

1. Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent [J] . Yudong Chen, Lili Su, Jiaming Xu Performance evaluation review . 2018,第1期

机译：对抗环境下的分布式统计机器学习：拜占庭式梯度下降
2. Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates [J] . Dong Yin, Yudong Chen, Ramchandran Kannan, JMLR: Workshop and Conference Proceedings . 2018,第3期

机译：拜占庭-鲁布特分布式学习：寻求最佳统计率
3. Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates [J] . Dong Yin, Yudong Chen, Ramchandran Kannan, JMLR: Workshop and Conference Proceedings . 2018,第12期

机译：拜占庭-鲁布特分布式学习：寻求最佳统计率
4. Distributed robust statistical learning: Byzantine mirror descent [C] . Dongsheng Ding, Xiaohan Wei, Mihailo R. Jovanovic IEEE Annual Conference on Decision and Control . 2019

机译：分布式强大的统计学习：拜占庭镜血液
5. Advancing Statistical Inference for Population Studies in Neuroimaging Using Machine Learning [D] . Varol, Erdem. 2018

机译：使用机器学习推进人口群体研究人口研究
6. Statistical inference to advance network models in epidemiology [O] . David Welch, Shweta Bansal, David R. Hunter -1

机译：统计推断在流行病学提前网络模型
7. Adversary-Resilient Distributed and Decentralized Statistical Inference and Machine Learning: An Overview of Recent Advances Under the Byzantine Threat Model [O] . Zhixiong Yang, Arpita Gang, Waheed U. Bajwa 2020

机译：逆境 - 弹性分布式和分散统计推理和机器学习：拜占庭威胁模型下最近进步的概述

Adversary-Resilient Distributed and Decentralized Statistical Inference and Machine Learning: An Overview of Recent Advances Under the Byzantine Threat Model

摘要

著录项

相似文献

相关主题

期刊订阅