본문

서브메뉴

Advances in Multi-agent Decision Making Systems With Adaptive Algorithms
Advances in Multi-agent Decision Making Systems With Adaptive Algorithms
Advances in Multi-agent Decision Making Systems With Adaptive Algorithms

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20250211151505
ISBN  
9798383213452
DDC  
621.3
저자명  
Verma, Ashwin.
서명/저자  
Advances in Multi-agent Decision Making Systems With Adaptive Algorithms
발행사항  
[Sl] : University of California, San Diego, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
165 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-01, Section: A.
주기사항  
Advisor: Touri, Behrouz.
학위논문주기  
Thesis (Ph.D.)--University of California, San Diego, 2024.
초록/해제  
요약With the growing demand for computation and the increasing prevalence of resource-constrained agents, the importance of leveraging a network of agents to solve complex problems has become often more pronounced. A multi-agent system consists of interconnected agents with computing capabilities, working collaboratively towards a shared objective. Distributed computation using a multi-agent system provides benefits with regards to privacy, reduction of computational load and resources. In this dissertation, we study two problems that benefit from being solved with the help of a multi-agent system namely (i) distributed convex optimization and (ii) distributed fact-checking. In part I, we consider a set of agents collaboratively solving a distributed convex optimization problem, asynchronously, under stringent communication constraints. In such situations, when an agent is activated and is allowed to communicate with only one of its neighbors, we would like to pick the one holding the most informative local estimate. We propose new algorithms where the agents with maximal dissent average their estimates, leading to an information mixing mechanism that often displays faster convergence to an optimal solution compared to randomized gossip.In Part II, we explore a distributed fact-checking system to detect fake news using inexpert agents. Each agent labels news as true or false based on its reliability, modeled as a Binary Symmetric Channel (BSC) with some error probability. We develop an algorithm that estimates statement validity by thresholding a linear combination of agents' labels and deriving optimal weights and thresholds to minimize error probability. Moreover, we present an adaptive algorithm to learn the agents' unreliability parameters and prove the convergence of the adaptive estimator. We also propose a broader class of adaptive estimators for the agents' unreliability parameters, providing the necessary conditions for convergence. We show that estimators for ensembles of two and three agents adhere to a consistent update rule, while hard-decoded estimates fail to converge for any number of agents.This dissertation contributes to the theoretical aspects of distributed optimization and fact-checking in multi-agent systems, offering novel algorithms and insights for efficient and reliable distributed decision-making.
일반주제명  
Electrical engineering
일반주제명  
Mathematics
일반주제명  
Engineering
일반주제명  
Systems science
일반주제명  
Information science
키워드  
Distributed optimization
키워드  
Fact-checking
키워드  
Multi-agent systems
키워드  
Stochastic approximation
키워드  
Convergence rates
기타저자  
University of California, San Diego Electrical and Computer Engineering
기본자료저록  
Dissertations Abstracts International. 86-01A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017161938
■00520250211151505
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798383213452
■035    ▼a(MiAaPQ)AAI31298703
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621.3
■1001  ▼aVerma,  Ashwin.
■24510▼aAdvances  in  Multi-agent  Decision  Making  Systems  With  Adaptive  Algorithms
■260    ▼a[Sl]▼bUniversity  of  California,  San  Diego▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a165  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-01,  Section:  A.
■500    ▼aAdvisor:  Touri,  Behrouz.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  San  Diego,  2024.
■520    ▼aWith  the  growing  demand  for  computation  and  the  increasing  prevalence  of  resource-constrained  agents,  the  importance  of  leveraging  a  network  of  agents  to  solve  complex  problems  has  become  often  more  pronounced.  A  multi-agent  system  consists  of  interconnected  agents  with  computing  capabilities,  working  collaboratively  towards  a  shared  objective.  Distributed  computation  using  a  multi-agent  system  provides  benefits  with  regards  to  privacy,  reduction  of  computational  load  and  resources.  In  this  dissertation,  we  study  two  problems  that  benefit  from  being  solved  with  the  help  of  a  multi-agent  system  namely  (i)  distributed  convex  optimization  and  (ii)  distributed  fact-checking.  In  part  I,  we  consider  a  set  of  agents  collaboratively  solving  a  distributed  convex  optimization  problem,  asynchronously,  under  stringent  communication  constraints.  In  such  situations,  when  an  agent  is  activated  and  is  allowed  to  communicate  with  only  one  of  its  neighbors,  we  would  like  to  pick  the  one  holding  the  most  informative  local  estimate.  We  propose  new  algorithms  where  the  agents  with  maximal  dissent  average  their  estimates,  leading  to  an  information  mixing  mechanism  that  often  displays  faster  convergence  to  an  optimal  solution  compared  to  randomized  gossip.In  Part  II,  we  explore  a  distributed  fact-checking  system  to  detect  fake  news  using  inexpert  agents.  Each  agent  labels  news  as  true  or  false  based  on  its  reliability,  modeled  as  a  Binary  Symmetric  Channel  (BSC)  with  some  error  probability.  We  develop  an  algorithm  that  estimates  statement  validity  by  thresholding  a  linear  combination  of  agents'  labels  and  deriving  optimal  weights  and  thresholds  to  minimize  error  probability.  Moreover,  we  present  an  adaptive  algorithm  to  learn  the  agents'  unreliability  parameters  and  prove  the  convergence  of  the  adaptive  estimator.  We  also  propose  a  broader  class  of  adaptive  estimators  for  the  agents'  unreliability  parameters,  providing  the  necessary  conditions  for  convergence.  We  show  that  estimators  for  ensembles  of  two  and  three  agents  adhere  to  a  consistent  update  rule,  while  hard-decoded  estimates  fail  to  converge  for  any  number  of  agents.This  dissertation  contributes  to  the  theoretical  aspects  of  distributed  optimization  and  fact-checking  in  multi-agent  systems,  offering  novel  algorithms  and  insights  for  efficient  and  reliable  distributed  decision-making.
■590    ▼aSchool  code:  0033.
■650  4▼aElectrical  engineering
■650  4▼aMathematics
■650  4▼aEngineering
■650  4▼aSystems  science
■650  4▼aInformation  science
■653    ▼aDistributed  optimization
■653    ▼aFact-checking
■653    ▼aMulti-agent  systems
■653    ▼aStochastic  approximation
■653    ▼aConvergence  rates
■690    ▼a0544
■690    ▼a0405
■690    ▼a0537
■690    ▼a0723
■690    ▼a0790
■71020▼aUniversity  of  California,  San  Diego▼bElectrical  and  Computer  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g86-01A.
■790    ▼a0033
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161938▼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
    TF14170 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.