Distributed Synchronous and Asynchronous Stochastic Optimization Algorithms over Networks

网络分布式同步和异步随机优化算法

• 批准号: 2012439
• 负责人: Ming Yan
• 金额: $ 20万
• 依托单位: Michigan State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-08-01 至 2023-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2012439&HistoricalAwards=false
• 关键词: Distributed; Synchronous; Asynchronous; Stochastic; Optimization

The number of installed internet of things (IoT) devices reached 26.66 billion in 2019, and this number will reach 75 billion by 2025. These devices collect massive volumes of datasets, and the analysis of these datasets can significantly improve our daily lives. However, how to process these datasets efficiently is still challenging. First, it is impossible to transfer all the data to a location because of the large volume and privacy concerns. Second, the networks formed by these devices are complex. Thus, existing distributed methods can not be directly applied to this scenario, and novel algorithms based on the communication between these devices have to be developed to make sense of these large-scale datasets.In this project, the PI will tackle the major drawbacks of existing decentralized consensus algorithms and greatly promote the efficiency and scalability of large-scale decentralized algorithms. To achieve this goal, the PI will systematically investigate the theoretical understanding of decentralized algorithms and two major challenges, i.e., large-scale data and large-scale networks. There are three objectives. The first objective is a better convergence rate for existing, and new, decentralized deterministic algorithms. The success of this objective will be the first step that will form the foundation of the next two objectives. The second objective is to develop decentralized stochastic algorithms with variance reduction for large-scale data. The last objective is asynchronous decentralized algorithms. This project will pave the way for new research endeavors to deal with large-scale distributed datasets and largely push the research boundaries of decentralized optimization in various application domains. This research will impact the use of decentralized algorithms in fields including wireless sensor networks, machine learning, the internet of things, and healthcare.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.

2019年物联网(IoT)设备安装数量达到266.6亿台，到2025年这一数字将达到750亿台。这些设备收集了大量的数据集，对这些数据集的分析可以显著改善我们的日常生活。然而，如何有效地处理这些数据集仍然是具有挑战性的。首先，由于数据量大和隐私问题，将所有数据转移到一个位置是不可能的。其次，这些设备形成的网络复杂。因此，现有的分布式方法不能直接应用于这种场景，必须开发基于这些设备之间通信的新算法来理解这些大规模数据集。在该项目中，PI将解决现有分散共识算法的主要缺陷，并极大地提高大规模分散算法的效率和可扩展性。为了实现这一目标，PI将系统地研究对分散算法的理论理解和两大挑战，即大规模数据和大规模网络。有三个目标。第一个目标是提高现有的和新的去中心化确定性算法的收敛速度。这一目标的成功将是构成下两个目标的基础的第一步。第二个目标是发展大规模数据的具有方差减少的分散随机算法。最后一个目标是异步分散算法。该项目将为处理大规模分布式数据集的新的研究努力铺平道路，并在很大程度上推动各种应用领域的分散优化的研究边界。这项研究将影响去中心化算法在无线传感器网络、机器学习、物联网和医疗保健等领域的使用。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势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

Phase retrieval from incomplete data via weighted nuclear norm minimization

• DOI: 10.1016/j.patcog.2022.108537
• 发表时间: 2022-01
• 期刊: Pattern Recognit.
• 作者: Zhi Li;Ming Yan;T. Zeng;Guixu Zhang

Image enhancement in active incoherent millimeter-wave imaging

主动非相干毫米波成像中的图像增强

• DOI: 10.1117/12.2585650
• 发表时间: 2021
• 作者: Vakalis, Stavros;Chen, Daniel;Yan, Ming;Nanzer, Jeffrey
• 通讯作者: Nanzer, Jeffrey

On the Linear Convergence of Two Decentralized Algorithms

两种去中心化算法的线性收敛性

• DOI: 10.1007/s10957-021-01833-y
• 发表时间: 2021
• 期刊: Journal of Optimization Theory and Applications
• 影响因子: 1.9
• 作者: Li, Yao;Yan, Ming
• 通讯作者: Yan, Ming

A Novel Regularization Based on the Error Function for Sparse Recovery

一种基于误差函数的新颖正则化稀疏恢复方法

• DOI: 10.1007/s10915-021-01443-w
• 发表时间: 2021
• 期刊: Journal of Scientific Computing
• 影响因子: 2.5
• 作者: Guo, Weihong;Lou, Yifei;Qin, Jing;Yan, Ming
• 通讯作者: Yan, Ming

Linear Convergent Decentralized Optimization with Compression

• 发表时间: 2020-07
• 期刊: ArXiv
• 作者: Xiaorui Liu;Yao Li;Rongrong Wang;Jiliang Tang;Ming Yan