본문

서브메뉴

Steering Machine Learning Ecosystems of Interacting Agents
Steering Machine Learning Ecosystems of Interacting Agents
Steering Machine Learning Ecosystems of Interacting Agents

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202103549
ISBN  
9798288866081
DDC  
004
저자명  
Jagadeesan, Meena.
서명/저자  
Steering Machine Learning Ecosystems of Interacting Agents
발행사항  
[Sl] : University of California, Berkeley, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
651 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
주기사항  
Advisor: Jordan, Michael I.;Steinhardt, Jacob.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2025.
초록/해제  
요약When machine learning models such as large language models (LLMs) and recommender systems are deployed into human-facing applications, these models interact with humans, companies, and other models within a broader ecosystem. However, the resulting multi-agent interactions often induce unintended ecosystem-level outcomes, including clickbait in classical content recommendation ecosystems, and more recently, safety violations and market concentration in nascent LLM ecosystems.The core issue is that ML models are classically analyzed as a single agent operating in isolation, so standard evaluation approaches in machine learning fail to capture ecosystem-level outcomes at the society-level, market-level, and algorithm-level. This thesis investigates how to characterize and steer ecosystem-level outcomes, focusing on LLM ecosystems and content recommendation ecosystems. To tackle this, we augment the typical algorithmic perspective on machine learning with an economic and statistical perspective. The key idea is to trace ecosystem-level outcomes back to the incentives of interacting agents (i.e., ML models, humans, and companies) and back to the ML pipeline for training models. In the first part, we investigate how competition between model-providers influences ecosystem-level performance trends and market outcomes. We demonstrate that scaling trends are fundamentally altered, and we develop technical tools to evaluate proposed AI policy. In the second part, we investigate how ML models deployed in content recommendation ecosystems influence content creation. We characterize how recommendation models shape the content supply via creator incentives, and how generative models shape which types of users produce content. In the third part, we investigate repeated interactions between a human and a ML model. We develop evaluation metrics which account for competing preferences, and design near-optimal incentive-aware algorithms. More broadly, this thesis takes a step towards a vision of machine learning ecosystems where the interactions between ML models, humans, and companies are steered towards the desired ecosystem-level outcomes.
일반주제명  
Computer science
키워드  
Large language models
키워드  
Recommender systems
키워드  
Machine learning
기타저자  
University of California, Berkeley Computer Science
기본자료저록  
Dissertations Abstracts International. 87-01B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017357703
■00520260202103549
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798288866081
■035    ▼a(MiAaPQ)AAI32041596
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aJagadeesan,  Meena.
■24510▼aSteering  Machine  Learning  Ecosystems  of  Interacting  Agents
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a651  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  B.
■500    ▼aAdvisor:  Jordan,  Michael  I.;Steinhardt,  Jacob.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2025.
■520    ▼aWhen  machine  learning  models  such  as  large  language  models  (LLMs)  and  recommender  systems  are  deployed  into  human-facing  applications,  these  models  interact  with  humans,  companies,  and  other  models  within  a  broader  ecosystem.  However,  the  resulting  multi-agent  interactions  often  induce  unintended  ecosystem-level  outcomes,  including  clickbait  in  classical  content  recommendation  ecosystems,  and  more  recently,  safety  violations  and  market  concentration  in  nascent  LLM  ecosystems.The  core  issue  is  that  ML  models  are  classically  analyzed  as  a  single  agent  operating  in  isolation,  so  standard  evaluation  approaches  in  machine  learning  fail  to  capture  ecosystem-level  outcomes  at  the  society-level,  market-level,  and  algorithm-level.    This  thesis  investigates  how  to  characterize  and  steer  ecosystem-level  outcomes,  focusing  on  LLM  ecosystems  and  content  recommendation  ecosystems.  To  tackle  this,  we  augment  the  typical  algorithmic  perspective  on  machine  learning  with  an  economic  and  statistical  perspective.  The  key  idea  is  to  trace  ecosystem-level  outcomes  back  to  the  incentives  of  interacting  agents  (i.e.,  ML  models,  humans,  and  companies)  and  back  to  the  ML  pipeline  for  training  models.  In  the  first  part,  we  investigate  how  competition  between  model-providers  influences  ecosystem-level  performance  trends  and  market  outcomes.  We  demonstrate  that  scaling  trends  are  fundamentally  altered,  and  we  develop  technical  tools  to  evaluate  proposed  AI  policy.  In  the  second  part,  we  investigate  how  ML  models  deployed  in  content  recommendation  ecosystems  influence  content  creation.  We  characterize  how  recommendation  models  shape  the  content  supply  via  creator  incentives,  and  how  generative  models  shape  which  types  of  users  produce  content.  In  the  third  part,  we  investigate  repeated  interactions  between  a  human  and  a  ML  model.  We  develop  evaluation  metrics  which  account  for  competing  preferences,  and  design  near-optimal  incentive-aware  algorithms.  More  broadly,  this  thesis  takes  a  step  towards  a  vision  of  machine  learning  ecosystems  where  the  interactions  between  ML  models,  humans,  and  companies  are  steered  towards  the  desired  ecosystem-level  outcomes.
■590    ▼aSchool  code:  0028.
■650  4▼aComputer  science
■653    ▼aLarge  language  models
■653    ▼aRecommender  systems
■653    ▼aMachine  learning
■690    ▼a0800
■690    ▼a0984
■71020▼aUniversity  of  California,  Berkeley▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g87-01B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357703▼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

    Info Détail de la recherche.

    • Réservation
    • n'existe pas
    • My Folder
    • Demande Première utilisation
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    Matériel
    Reg No. Call No. emplacement Status Lend Info
    TF18932 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Les réservations sont disponibles dans le livre d'emprunt. Pour faire des réservations, S'il vous plaît cliquer sur le bouton de réservation

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.