CAREER: Towards a Communication Foundation for Distributed and Decentralized Machine Learning

职业:为分布式和去中心化机器学习建立通信基础

基本信息

  • 批准号:
    2143559
  • 负责人:
  • 金额:
    $ 50万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2022
  • 资助国家:
    美国
  • 起止时间:
    2022-09-01 至 2027-08-31
  • 项目状态:
    未结题

项目摘要

With the emerging paradigm shift towards moving the data collection and machine learning (ML) model training to the edge, distributed and decentralized ML has become increasingly critical to empowering many applications, such as autonomous driving, recommender systems, and Internet of Things (IoT). This trend imposes formidable challenges on the underlying communication design and catalyzes its evolution from connecting people and connecting things to connecting intelligence. This CAREER project develops fundamental communication technologies to enable distributed and decentralized ML in next-generation wireless systems. It transforms wireless communications from pure data transfer to intelligence transfer, building a synergy between communications and ML in a closely integrated fashion. In partnership with industry, results enabled by this project can be prototyped and integrated into real systems, potentially impacting 6G standardization and other future communication systems. The cross disciplinary nature of this project naturally translates into case studies and new development in a number of undergraduate and graduate level courses, by integrating ML and AI to the curriculum of communications and networking. The education and outreach activities will collectively promote a common thread of providing the best opportunities for diverse groups of bright young minds to develop into future scientists and engineers.This project aims at developing the theoretical foundation and novel communication algorithms for distributed and decentralized ML, thereby catalyzing a paradigm shift of wireless communications towards connecting intelligence. Towards this end, this project will develop a novel random orthogonalization principle that tightly integrates physical layer communications with ML. Additionally, the research will study the impact of fading and noisy channels on the performance of ML, and design communication methods to improve the accuracy and convergence of the ML tasks. Finally, a novel adaptive communication method for distributed and decentralized multi-armed bandits will be investigated, where coding and interleaving designs for online learning with adversarial communications will be studied. The proposed research promotes the fundamental understanding of the synergy between distributed and decentralized ML and communications, and will have broad applications beyond the specific problems studied in this project.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
随着数据收集和机器学习(ML)模型训练向边缘转移的新范式转变,分布式和分散式ML对于增强许多应用程序(如自动驾驶,推荐系统和物联网(IoT))变得越来越重要。这一趋势对底层的通信设计提出了巨大的挑战,并促进了其从连接人和连接物到连接智能的演变。这个CAREER项目开发基础通信技术,以在下一代无线系统中实现分布式和分散式ML。它将无线通信从纯粹的数据传输转变为智能传输,以紧密集成的方式在通信和ML之间建立协同作用。通过与行业合作,该项目实现的成果可以原型化并集成到真实的系统中,这可能会影响6G标准化和其他未来的通信系统。该项目的跨学科性质自然转化为案例研究和一些本科生和研究生课程的新发展,通过将ML和AI整合到通信和网络课程中。教育和推广活动将共同促进一个共同的主线,为不同群体的聪明的年轻人提供最好的机会,发展成为未来的科学家和工程师。该项目旨在为分布式和去中心化的ML开发理论基础和新颖的通信算法,从而催化无线通信向连接智能的范式转变。为此,该项目将开发一种新的随机正交化原理,将物理层通信与ML紧密集成。此外,研究衰落和噪声信道对ML性能的影响,并设计通信方法以提高ML任务的准确性和收敛性。最后,一种新的自适应通信方法的分布式和分散的多武装土匪将研究,编码和交织设计的在线学习与对抗通信。该研究将促进对分布式和去中心化机器学习与通信之间协同作用的基本理解,并将在本项目研究的具体问题之外具有广泛的应用。该奖项反映了NSF的法定使命,并通过使用基金会的知识价值和更广泛的影响审查标准进行评估,被认为值得支持。

项目成果

期刊论文数量(10)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game
  • DOI:
    10.48550/arxiv.2205.15512
  • 发表时间:
    2022-05
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Wei Xiong;Han Zhong;Chengshuai Shi;Cong Shen;Liwei Wang;T. Zhang
  • 通讯作者:
    Wei Xiong;Han Zhong;Chengshuai Shi;Cong Shen;Liwei Wang;T. Zhang
Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints
  • DOI:
    10.48550/arxiv.2306.06265
  • 发表时间:
    2023-06
  • 期刊:
  • 影响因子:
    2.4
  • 作者:
    Donghao Li;Ruiquan Huang;Cong Shen;Jing Yang
  • 通讯作者:
    Donghao Li;Ruiquan Huang;Cong Shen;Jing Yang
Exploiting Feature Heterogeneity for Improved Generalization in Federated Multi-task Learning
Teaching Reinforcement Learning Agents via Reinforcement Learning
通过强化学习教授强化学习代理
Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources
  • DOI:
    10.48550/arxiv.2306.08364
  • 发表时间:
    2023-06
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Chengshuai Shi;Wei Xiong;Cong Shen;Jing Yang
  • 通讯作者:
    Chengshuai Shi;Wei Xiong;Cong Shen;Jing Yang
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Cong Shen其他文献

Stability analysis for interval time-varying delay systems based on time-varying bound integral method
基于时变界限积分法的区间时变时滞系统稳定性分析
  • DOI:
    10.1016/j.jfranklin.2014.07.015
  • 发表时间:
    2014-10
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Qian Wei;Li Tao;Cong Shen;Fei Shumin
  • 通讯作者:
    Fei Shumin
Stochastic Linear Contextual Bandits with Diverse Contexts
具有不同上下文的随机线性上下文强盗
Output-feedback stabilization control of systems with random switchings and state jumps
具有随机切换和状态跳跃的系统的输出反馈稳定控制
Multi-relation graph embedding for predicting miRNA-target gene interactions by integrating gene sequence information
通过整合基因序列信息预测 miRNA-靶基因相互作用的多关系图嵌入
On the Design of Modern Multilevel Coded Modulation for Unequal Error Protection
论现代多级编码调制的不等差错保护设计

Cong Shen的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Cong Shen', 18)}}的其他基金

Collaborative Research: CPS Medium: Learning through the Air: Cross-Layer UAV Orchestration for Online Federated Optimization
合作研究:CPS 媒介:空中学习:用于在线联合优化的跨层无人机编排
  • 批准号:
    2313110
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
CCSS: Collaborative Research: Towards a Resource Rationing Framework for Wireless Federated Learning
CCSS:协作研究:无线联邦学习的资源配给框架
  • 批准号:
    2033671
  • 财政年份:
    2020
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
Collaborative Research: MLWiNS: Dino-RL: A Domain Knowledge Enriched Reinforcement Learning Framework for Wireless Network Optimization
合作研究:MLWiNS:Dino-RL:用于无线网络优化的领域知识丰富的强化学习框架
  • 批准号:
    2002902
  • 财政年份:
    2020
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
Collaborative Research: SWIFT: SMALL: Learning-Efficient Spectrum Access for No-Sensing Devices in Shared Spectrum
合作研究:SWIFT:SMALL:共享频谱中无感知设备的学习高效频谱访问
  • 批准号:
    2029978
  • 财政年份:
    2020
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant

相似海外基金

CAREER: Towards a complete picture of communication in anthropogenic noise - Auditory processing among urban and rural soundscapes.
职业:全面了解人为噪音中的交流——城市和乡村声景中的听觉处理。
  • 批准号:
    2414003
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Continuing Grant
CAREER: Towards Privacy-Preserving Wireless Communication: Fundamental Limits and Coding Schemes
职业:走向保护隐私的无线通信:基本限制和编码方案
  • 批准号:
    2401373
  • 财政年份:
    2023
  • 资助金额:
    $ 50万
  • 项目类别:
    Continuing Grant
Investigation of Opinion Polarization in Online Communication: Towards an Integration of Explanation and Prediction
在线交流中意见两极分化的调查:走向解释与预测的整合
  • 批准号:
    22K20182
  • 财政年份:
    2022
  • 资助金额:
    $ 50万
  • 项目类别:
    Grant-in-Aid for Research Activity Start-up
CAREER: Towards Realizing Timely Information Transfer and Processing for Networked Communication Systems
职业:实现网络通信系统的及时信息传输和处理
  • 批准号:
    2146099
  • 财政年份:
    2022
  • 资助金额:
    $ 50万
  • 项目类别:
    Continuing Grant
CAREER: Towards a complete picture of communication in anthropogenic noise - Auditory processing among urban and rural soundscapes.
职业:全面了解人为噪音中的交流——城市和乡村声景中的听觉处理。
  • 批准号:
    2145793
  • 财政年份:
    2022
  • 资助金额:
    $ 50万
  • 项目类别:
    Continuing Grant
Towards Efficient Communication in Multi-Agent Deep Reinforcement Learning
实现多智能体深度强化学习中的高效通信
  • 批准号:
    572694-2022
  • 财政年份:
    2022
  • 资助金额:
    $ 50万
  • 项目类别:
    University Undergraduate Student Research Awards
EAGER: Towards robust, interpretable deep learning via communication theory and neuro-inspiration
EAGER:通过沟通理论和神经灵感实现稳健、可解释的深度学习
  • 批准号:
    2224263
  • 财政年份:
    2022
  • 资助金额:
    $ 50万
  • 项目类别:
    Standard Grant
CAREER: Towards Practical Mobile Visible Light Communication
职业:迈向实用的移动可见光通信
  • 批准号:
    2146267
  • 财政年份:
    2022
  • 资助金额:
    $ 50万
  • 项目类别:
    Continuing Grant
Rethinking brain-computer interface design: Towards user-centric performance evaluation, algorithm development, and training methods to improve and increase access to aided communication technologies
重新思考脑机接口设计:走向以用户为中心的性能评估、算法开发和培训方法,以改进和增加辅助通信技术的使用
  • 批准号:
    568804-2022
  • 财政年份:
    2022
  • 资助金额:
    $ 50万
  • 项目类别:
    Alexander Graham Bell Canada Graduate Scholarships - Doctoral
CAREER: Towards Privacy-Preserving Wireless Communication: Fundamental Limits and Coding Schemes
职业:走向保护隐私的无线通信:基本限制和编码方案
  • 批准号:
    2047913
  • 财政年份:
    2021
  • 资助金额:
    $ 50万
  • 项目类别:
    Continuing Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了