CAREER: Leveraging Sparsity in Massively Distributed Optimization

职业：在大规模分布式优化中利用稀疏性

• 批准号: 1750539
• 负责人: Stratis Ioannidis
• 金额: $ 45.87万
• 依托单位: Northeastern University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-02-01 至 2025-01-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1750539&HistoricalAwards=false
• 关键词: CAREER; Leveraging; Sparsity; Massively; Distributed

This project develops novel parallel optimization techniques based on the Frank-Wolfe algorithm, enabling the massive parallelization, at an unprecedented scale, of several problems of key significance to computer science, engineering, and operations research. Massively parallelizing such problems can have a significant practical impact on both academia and industry. Using Apache Spark as a development platform, algorithms developed by the project can be implemented, deployed and evaluated over hundreds of machines and thousands of CPUs. The Massachusetts Green High Performance Computing Center (MGHPCC) as well as cloud services, such as Amazon Web Services and the Google Cloud Platform, are leveraged for this deployment, demonstrating both the scalability of developed algorithms as well as their applicability to commercial cluster environments. Educational activities are closely integrated with this research agenda, including a course developed by the principal investigator using MGHPCC as a computing platform, and outreach activities developed jointly with Northeastern University's Center for STEM Education.This research advances our knowledge and understanding of the formal conditions under which problems can be massively parallelized via map-reduce implementations of the Frank-Wolfe algorithm. The project leverages sparsity properties that optimization problems exhibit under Frank-Wolfe, thereby enabling their parallelization via map-reduce operations. Beyond tailored, problem-specific implementations, the project identifies formal, structural properties of problems (or, classes of problems) under which such massive parallelization via map-reduce is possible. The use of Frank-Wolfe as a building block for parallelization, both in convex optimization but also in submodular maximization settings, is transformative. In the latter case, it amounts to a non-combinatorial approach for parallelization, attaining the same approximation guarantee as serial algorithms.

该项目开发了基于Frank-Wolfe算法的新型并行优化技术，使计算机科学，工程和运筹学中具有关键意义的几个问题能够以前所未有的规模大规模并行化。大规模并行处理这些问题可以对学术界和工业界产生重大的实际影响。使用Apache Spark作为开发平台，该项目开发的算法可以在数百台机器和数千个CPU上实现，部署和评估。该部署利用了马萨诸塞州绿色高性能计算中心（MGHPCC）以及Amazon Web Services和Google Cloud Platform等云服务，展示了所开发算法的可扩展性及其对商业集群环境的适用性。教育活动与这项研究议程紧密结合，包括由首席研究员使用MGHPCC作为计算平台开发的课程，以及与东北大学STEM教育中心联合开发的推广活动。这项研究推进了我们对问题可以通过Frank-Wolfe算法的映射缩减实现大规模并行化的形式条件的知识和理解。该项目利用了在Frank-Wolfe下优化问题表现出的稀疏性属性，从而通过映射缩减操作实现了并行化。除了量身定制的特定问题的实现之外，该项目还确定了问题（或问题类）的形式化结构属性，在这些属性下，通过map-reduce进行大规模并行化是可能的。在凸优化和次模最大化设置中，使用Frank-Wolfe作为并行化的构建块是变革性的。在后一种情况下，它相当于并行化的非组合方法，获得与串行算法相同的近似保证。

项目成果

Rate Allocation and Content Placement in Cache Networks

缓存网络中的速率分配和内容放置

• DOI: 10.1109/infocom42981.2021.9488715
• 发表时间: 2021
• 期刊: IEEE INFOCOM 2021 - IEEE Conference on Computer Communications
• 作者: Kamran, Khashayar;Moharrer, Armin;Ioannidis, Stratis;Yeh, Edmund
• 通讯作者: Yeh, Edmund

AlignGraph: A Group of Generative Models for Graphs

• DOI: 10.48550/arxiv.2301.11273
• 发表时间: 2023-01
• 作者: Kimia Shayestehfard;Dana Brooks;Stratis Ioannidis

Jointly Optimal Routing and Caching with Bounded Link Capacities

具有有限链路容量的联合最优路由和缓存

• DOI: 10.1109/icc45041.2023.10279235
• 发表时间: 2023
• 期刊: ICC 2023 - IEEE International Conference on Communications
• 作者: Li, Yuanyuan;Zhang, Yuchao;Ioannidis, Stratis;Crowcroft, Jon
• 通讯作者: Crowcroft, Jon

Massively Distributed Graph Distances

• DOI: 10.1109/tsipn.2020.3022003
• 发表时间: 2020
• 期刊: IEEE Transactions on Signal and Information Processing over Networks
• 影响因子: 3.2
• 作者: Armin Moharrer;Jasmin Gao;Shikun Wang;José Bento;Stratis Ioannidis

Variational Inference from Ranked Samples with Features

从具有特征的排序样本进行变分推断

• 发表时间: 2019
• 期刊: Proceedings of Machine Learning Research
• 作者: Guo, Y.;Dy, J.;D., Kalpathy-Cramer;Ostmo, S.;Campbell, J.P.;Chiang, M.F.;Ioannidis, S.
• 通讯作者: Ioannidis, S.