東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

A Unified Framework for Understandin...

Zhang, Xinwei.

FindBook

Google Book

Amazon

博客來

A Unified Framework for Understanding Distributed Optimization Algorithms: System Design and Its Applications.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	A Unified Framework for Understanding Distributed Optimization Algorithms: System Design and Its Applications./
作者:	Zhang, Xinwei.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
面頁冊數:	215 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-06, Section: B.
Contained By:	Dissertations Abstracts International85-06B.
標題:	Electrical engineering. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30811044
ISBN:	9798381175844

A Unified Framework for Understanding Distributed Optimization Algorithms: System Design and Its Applications.
Zhang, Xinwei.

A Unified Framework for Understanding Distributed Optimization Algorithms: System Design and Its Applications. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 215 p.

Source: Dissertations Abstracts International, Volume: 85-06, Section: B.

Thesis (Ph.D.)--University of Minnesota, 2023.

This item must not be sold to any third party vendors.

More than ever before, technology advances across the spectrum have meant that we have individualized and decentralized access to data, resources, and human capital. The capability to utilize massively and distributedly generated data (e.g., personal shopping records) and distributed computation (e.g., fast smartphone processors) has simplified our lives, facilitated optimal resource allocation, and unlocked innovation across industries. Distributed algorithms play a central role in the optimal operation of distributed systems in many applications, such as machine learning, signal processing, and control. Significant research efforts have been devoted to developing and analyzing new algorithms for various applications. However, existing methods are still facing difficulties in using computational resources and distributed data safely and efficiently. The three major challenges in state-of-the-art distributed systems are 1) finding appropriate models to describe the resources and problems in the system, 2) developing a general approach to solving problems efficiently, and 3) ensuring participants' privacy. My thesis research focuses on building an algorithmic framework to resolve these fundamental and practical challenges. This thesis provides a fresh perspective to understand, analyze, and design distributed optimization algorithms. Through the lens of multi-rate feedback control, this thesis theoretically proves that a wide class of distributed algorithms, including popular decentralized and federated schemes, can be viewed as discretizing a certain continuous-time feedback control system, possibly with multiple sampling rates, while preserving the same convergence behavior. Further, the proposed system unifies the stochasticities in a wide range of distributed optimization algorithms as several types of noises injected into the control system, and provides a uniform convergence analysis to a class of distributed stochastic optimization algorithms. The control-based framework is applied to designing new algorithms in decentralized optimization and federated learning to meet different system requirements including achieving convergence, optimal performance, or meeting privacy concerns. In summary, this thesis establishes a control-based framework to understand, analyze, and design distributed optimization algorithms, with applications in decentralized optimization and federated learning algorithm design.

ISBN: 9798381175844Subjects--Topical Terms:

649834
Electrical engineering.
Subjects--Index Terms:

Control theory

A Unified Framework for Understanding Distributed Optimization Algorithms: System Design and Its Applications.
LDR:03698nmm a2200385 4500 001 2395589
005 20240517104630.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798381175844
035 $a (MiAaPQ)AAI30811044
035 $a AAI30811044
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhang, Xinwei. $3 1287325
245 1 2 $a A Unified Framework for Understanding Distributed Optimization Algorithms: System Design and Its Applications.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 215 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-06, Section: B.
500 $a Advisor: Hong, Mingyi;Dhople, Sairaj.
502 $a Thesis (Ph.D.)--University of Minnesota, 2023.
506 $a This item must not be sold to any third party vendors.
520 $a More than ever before, technology advances across the spectrum have meant that we have individualized and decentralized access to data, resources, and human capital. The capability to utilize massively and distributedly generated data (e.g., personal shopping records) and distributed computation (e.g., fast smartphone processors) has simplified our lives, facilitated optimal resource allocation, and unlocked innovation across industries. Distributed algorithms play a central role in the optimal operation of distributed systems in many applications, such as machine learning, signal processing, and control. Significant research efforts have been devoted to developing and analyzing new algorithms for various applications. However, existing methods are still facing difficulties in using computational resources and distributed data safely and efficiently. The three major challenges in state-of-the-art distributed systems are 1) finding appropriate models to describe the resources and problems in the system, 2) developing a general approach to solving problems efficiently, and 3) ensuring participants' privacy. My thesis research focuses on building an algorithmic framework to resolve these fundamental and practical challenges. This thesis provides a fresh perspective to understand, analyze, and design distributed optimization algorithms. Through the lens of multi-rate feedback control, this thesis theoretically proves that a wide class of distributed algorithms, including popular decentralized and federated schemes, can be viewed as discretizing a certain continuous-time feedback control system, possibly with multiple sampling rates, while preserving the same convergence behavior. Further, the proposed system unifies the stochasticities in a wide range of distributed optimization algorithms as several types of noises injected into the control system, and provides a uniform convergence analysis to a class of distributed stochastic optimization algorithms. The control-based framework is applied to designing new algorithms in decentralized optimization and federated learning to meet different system requirements including achieving convergence, optimal performance, or meeting privacy concerns. In summary, this thesis establishes a control-based framework to understand, analyze, and design distributed optimization algorithms, with applications in decentralized optimization and federated learning algorithm design.
590 $a School code: 0130.
650 4 $a Electrical engineering. $3 649834
650 4 $a Computer engineering. $3 621879
653 $a Control theory
653 $a Distributed optimization
653 $a Federated learning
653 $a Non-convex optimization
690 $a 0544
690 $a 0464
690 $a 0800
710 2 $a University of Minnesota. $b Electrical/Computer Engineering. $3 1672573
773 0 $t Dissertations Abstracts International $g 85-06B.
790 $a 0130
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30811044