Decomposition Framework for Non-convex Nonsmooth Optimization with Applications in Data Analytics

非凸非光滑优化的分解框架及其在数据分析中的应用

• 批准号: 1727757
• 负责人: Mingyi Hong
• 金额: $ 42.68万
• 依托单位: University of Minnesota-Twin Cities
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-08-15 至 2023-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1727757&HistoricalAwards=false
• 关键词: Decomposition; Framework; Non; convex; Nonsmooth

Rapid advances in sensor, communication and storage technologies have led to the availability of data on an unprecedented scale. Depending on the source, these data may represent measurements, images, texts, time-series and a variety of other formats. Significant challenges remain in translating the increasing amount of data to useful and actionable information. The objective of this project is to address this information dilemma through the lens of modern large-scale optimization. This project supports research on methods to effectively process large-scale, unstructured, complex data so as to be usable in applications such as bioinformatics, smart energy systems, manufacturing, and healthcare. The project will also engage graduate students in the research activities and will support outreach to undergraduate STEM students through an existing program at the PI's university. This project will focus on the construction of a general optimization and computational framework that enables a number of promising but challenging large-scale data-intensive applications. The research comprises two major thrusts. The first will build and analyze a novel optimization-based primal-dual decomposition framework that transforms a large, tightly coupled, non-convex problem into a sequence of independent subproblems solvable by parallel machines. The second applies the decomposition framework to a number of important emerging data-intensive applications, including high-dimensional clustering, topic modeling, and robust high-dimensional regression. Fundamental questions, such as optimality, convergence rates, and scalability in high dimension will be investigated. The project will test the developed methods using data from two important energy applications: smart energy meters and real-time residential photovoltaic inverters.

传感器，通信和存储技术的快速进步导致了前所未有的数据的可用性。 根据来源，这些数据可能代表测量，图像，文本，时间序列和各种其他格式。 在将越来越多的数据转换为有用且可操作的信息方面仍然存在重大挑战。该项目的目的是通过现代大规模优化的视角解决这一信息困境。 该项目支持对有效处理大规模，非结构化，复杂数据的方法的研究，以便在生物信息学，智能能源系统，制造业和医疗保健等应用中可用。 该项目还将吸引研究生参加研究活动，并通过PI大学的现有计划来支持对本科STEM学生的宣传。该项目将着重于建造一般优化和计算框架，该框架可以实现许多有希望但具有挑战性的大规模数据密集型应用程序。 该研究包括两个主要推力。 第一个将构建和分析一个基于优化的原始偶性分解框架，该框架将大型，紧密耦合的非凸问题转换为可通过并行机器解决的独立子问题序列。 第二个将分解框架应用于许多重要的新兴数据密集型应用程序，包括高维聚类，主题建模和强大的高维回归。 将研究基本问题，例如最优性，收敛速率和高维度的可伸缩性。 该项目将使用来自两个重要能源应用的数据测试开发的方法：智能能量计和实时住宅光伏逆变器。

项目成果

Perturbed proximal primal–dual algorithm for nonconvex nonsmooth optimization

• DOI: 10.1007/s10107-019-01365-4
• 发表时间: 2019-02
• 期刊: Mathematical Programming
• 影响因子: 2.7
• 作者: Davood Hajinezhad;Mingyi Hong

Distributed Adversarial Training to Robustify Deep Neural Networks at Scale

• DOI: 10.48550/arxiv.2206.06257
• 发表时间: 2022-06
• 作者: Gaoyuan Zhang;Songtao Lu;Yihua Zhang;Xiangyi Chen;Pin-Yu Chen;Quanfu Fan;Lee Martie;L. Horesh

Fast and Global Optimal Nonconvex Matrix Factorization via Perturbed Alternating Proximal Point

通过扰动交替近点的快速全局最优非凸矩阵分解

• DOI: 10.1109/icassp.2019.8682941
• 发表时间: 2019
• 期刊: IEEE ICASSP
• 作者: Lu, Songtao;Hong, Mingyi;Wang, Zhengdao
• 通讯作者: Wang, Zhengdao

Understanding a Class of Decentralized and Federated Optimization Algorithms: A Multirate Feedback Control Perspective

了解一类分散式联合优化算法：多速率反馈控制视角

• DOI: 10.1137/22m1475648
• 发表时间: 2023
• 期刊: SIAM Journal on Optimization
• 影响因子: 3.1
• 作者: Zhang, Xinwei;Hong, Mingyi;Elia, Nicola
• 通讯作者: Elia, Nicola

Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy

• 发表时间: 2021-06
• 作者: Xinwei Zhang;Xiangyi Chen;Min-Fong Hong;Zhiwei Steven Wu;Jinfeng Yi