서브메뉴
검색
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
- 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
- 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
Info Détail de la recherche.
- Réservation
- n'existe pas
- My Folder
- Demande Première utilisation
- Non-Book Loan Application
- Nighttime Book Loan Application
Available after logging in.


