본문

서브메뉴

Distributed Multi-Agent Learning Under Federated and Competitive Settings
Distributed Multi-Agent Learning Under Federated and Competitive Settings
Distributed Multi-Agent Learning Under Federated and Competitive Settings

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202105653
ISBN  
9798265452399
DDC  
658
저자명  
Qin, Tiancheng.
서명/저자  
Distributed Multi-Agent Learning Under Federated and Competitive Settings
발행사항  
[Sl] : University of Illinois at Urbana-Champaign, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
91 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-06, Section: B.
주기사항  
Advisor: Etesami, Rasoul.
학위논문주기  
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2024.
초록/해제  
요약In recent years, the landscape of artificial intelligence (AI) has undergone a transformative evolution, transitioning from traditional single-agent approaches to more sophisticated and collaborative frameworks. The convergence of distributed computing and multi-agent systems has given rise to the powerful and versatile field of distributed multi-agent learning, allowing multiple agents to collaboratively learn and adapt in complex and dynamic environments. This intersection of distributed computing and multi-agent systems has ushered in a new era of intelligent systems capable of tackling intricate problems that were once deemed insurmountable for a single entity. Among the various topics in the field, in this thesis, we focus on two that bear significant importance, namely, Federated Learning and Learning in Stochastic Games.Federated Learning represents a paradigm shift from traditional centralized models, offering a decentralized approach where model training occurs locally on individual devices or servers, and only aggregated updates are shared. This transformative technique not only preserves data privacy but also addresses the challenges posed by the growing volume and diversity of data in our interconnected world.On the other hand, moving further from a collaborative scheme to a potentially competitive one, stochastic games emerge as a powerful framework to model multi-agent decision-making under uncertainty. Unlike traditional games, where players operate in a deterministic environment, stochastic games embrace the inherent unpredictability of real-world scenarios, where chance events and the actions of other players shape the unfolding dynamics. This nuanced approach enables modeling a wide range of complex systems, from economic competitions and environmental negotiations to multi-agent robotic interactions.In this thesis, we first analyze the convergence rate of the local stochastic gradient descent (SGD) algorithm (also known as Federated Averaging), arguably the most well-known and widely-used distributed optimization algorithm for Federated learning. Our contributions can be divided into two categories: (i) analysis of the effect of local steps in the convergence rate of Local SGD and (ii) analysis of the convergence rate of Local SGD for over-parameterized models. After that, we move further to the competitive scheme of stochastic games. Specifically, we study a subclass of n-player stochastic games, namely, stochastic games with independent chains and unknown transition matrices, and propose a scalable and independent decentralized learning algorithm that is provably convergent to the set of ε-Nash equilibrium policies.
일반주제명  
Industrial engineering
일반주제명  
Robotics
키워드  
Distributed learning
키워드  
Federated learning
키워드  
Stochastic games
키워드  
Stochastic gradient descent
기타저자  
University of Illinois at Urbana-Champaign Industrial&Enterprise Sys Eng
기본자료저록  
Dissertations Abstracts International. 87-06B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2024        us                              c    eng  d
■001000017361019
■00520260202105653
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798265452399
■035    ▼a(MiAaPQ)AAI32409641
■035    ▼a(MiAaPQ)124485
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a658
■1001  ▼aQin,  Tiancheng.
■24510▼aDistributed  Multi-Agent  Learning  Under  Federated  and  Competitive  Settings
■260    ▼a[Sl]▼bUniversity  of  Illinois  at  Urbana-Champaign▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a91  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-06,  Section:  B.
■500    ▼aAdvisor:  Etesami,  Rasoul.
■5021  ▼aThesis  (Ph.D.)--University  of  Illinois  at  Urbana-Champaign,  2024.
■520    ▼aIn  recent  years,  the  landscape  of  artificial  intelligence  (AI)  has  undergone  a  transformative  evolution,  transitioning  from  traditional  single-agent  approaches  to  more  sophisticated  and  collaborative  frameworks.  The  convergence  of  distributed  computing  and  multi-agent  systems  has  given  rise  to  the  powerful  and  versatile  field  of  distributed  multi-agent  learning,  allowing  multiple  agents  to  collaboratively  learn  and  adapt  in  complex  and  dynamic  environments.  This  intersection  of  distributed  computing  and  multi-agent  systems  has  ushered  in  a  new  era  of  intelligent  systems  capable  of  tackling  intricate  problems  that  were  once  deemed  insurmountable  for  a  single  entity.  Among  the  various  topics  in  the  field,  in  this  thesis,  we  focus  on  two  that  bear  significant  importance,  namely,  Federated  Learning  and  Learning  in  Stochastic  Games.Federated  Learning  represents  a  paradigm  shift  from  traditional  centralized  models,  offering  a  decentralized  approach  where  model  training  occurs  locally  on  individual  devices  or  servers,  and  only  aggregated  updates  are  shared.  This  transformative  technique  not  only  preserves  data  privacy  but  also  addresses  the  challenges  posed  by  the  growing  volume  and  diversity  of  data  in  our  interconnected  world.On  the  other  hand,  moving  further  from  a  collaborative  scheme  to  a  potentially  competitive  one,  stochastic  games  emerge  as  a  powerful  framework  to  model  multi-agent  decision-making  under  uncertainty.  Unlike  traditional  games,  where  players  operate  in  a  deterministic  environment,  stochastic  games  embrace  the  inherent  unpredictability  of  real-world  scenarios,  where  chance  events  and  the  actions  of  other  players  shape  the  unfolding  dynamics.  This  nuanced  approach  enables  modeling  a  wide  range  of  complex  systems,  from  economic  competitions  and  environmental  negotiations  to  multi-agent  robotic  interactions.In  this  thesis,  we  first  analyze  the  convergence  rate  of  the  local  stochastic  gradient  descent  (SGD)  algorithm  (also  known  as  Federated  Averaging),  arguably  the  most  well-known  and  widely-used  distributed  optimization  algorithm  for  Federated  learning.  Our  contributions  can  be  divided  into  two  categories:  (i)  analysis  of  the  effect  of  local  steps  in  the  convergence  rate  of  Local  SGD  and  (ii)  analysis  of  the  convergence  rate  of  Local  SGD  for  over-parameterized  models.  After  that,  we  move  further  to  the  competitive  scheme  of  stochastic  games.  Specifically,  we  study  a  subclass  of  n-player  stochastic  games,  namely,  stochastic  games  with  independent  chains  and  unknown  transition  matrices,  and  propose  a  scalable  and  independent  decentralized  learning  algorithm  that  is  provably  convergent  to  the  set  of  ε-Nash  equilibrium  policies.
■590    ▼aSchool  code:  0090.
■650  4▼aIndustrial  engineering
■650  4▼aRobotics
■653    ▼aDistributed  learning
■653    ▼aFederated  learning
■653    ▼aStochastic  games
■653    ▼aStochastic  gradient  descent
■690    ▼a0796
■690    ▼a0800
■690    ▼a0546
■690    ▼a0771
■71020▼aUniversity  of  Illinois  at  Urbana-Champaign▼bIndustrial&Enterprise  Sys  Eng.
■7730  ▼tDissertations  Abstracts  International▼g87-06B.
■790    ▼a0090
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17361019▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF16505 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.