서브메뉴
검색
Probabilistic Inference in the Era of Large Models
Probabilistic Inference in the Era of Large Models
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151405
- ISBN
- 9798382230467
- DDC
- 004
- 저자명
- Shih, Andy.
- 서명/저자
- Probabilistic Inference in the Era of Large Models
- 발행사항
- [Sl] : Stanford University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 138 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
- 주기사항
- Advisor: Stefano Ermon;Dorsa Sadigh.
- 학위논문주기
- Thesis (Ph.D.)--Stanford University, 2024.
- 초록/해제
- 요약Recent progression in generative artificial intelligence has witnessed a ballooning in model size and data dimensionality. These large models, however, come with increased computational demands which prohibit the use of many traditional probabilistic inference algorithms. There is a pressing need for new inference algorithms that are efficient enough to run on large models and modern architectures, and powerful enough to work with high dimensionalities and large datasets.In this dissertation, we address this challenge by designing algorithms using ingredients that are compatible with model scale, such as parallelization, amortized inference, and neural function approximations. We present a variety of techniques to improve sampling and inference, leading to faster sample speed, better flexibility of sample queries, and more accurate estimation of inference targets. Our methods are applicable to large models across a range of architectures such as diffusion, autoregressive, and masked-autoencoder models. We demonstrate these findings on applications spanning image and text generation, game-playing, and robotics domains. These insights lead to practical improvements and novel perspectives for efficiently deploying large-scale generative models.
- 일반주제명
- Computer science
- 키워드
- Robotics domains
- 기타저자
- Stanford University.
- 기본자료저록
- Dissertations Abstracts International. 85-11B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017161502
■00520250211151405
■006m o d
■007cr#unu||||||||
■020 ▼a9798382230467
■035 ▼a(MiAaPQ)AAI31255810
■035 ▼a(MiAaPQ)nt653cd4468
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aShih, Andy.
■24510▼aProbabilistic Inference in the Era of Large Models
■260 ▼a[Sl]▼bStanford University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a138 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-11, Section: B.
■500 ▼aAdvisor: Stefano Ermon;Dorsa Sadigh.
■5021 ▼aThesis (Ph.D.)--Stanford University, 2024.
■520 ▼aRecent progression in generative artificial intelligence has witnessed a ballooning in model size and data dimensionality. These large models, however, come with increased computational demands which prohibit the use of many traditional probabilistic inference algorithms. There is a pressing need for new inference algorithms that are efficient enough to run on large models and modern architectures, and powerful enough to work with high dimensionalities and large datasets.In this dissertation, we address this challenge by designing algorithms using ingredients that are compatible with model scale, such as parallelization, amortized inference, and neural function approximations. We present a variety of techniques to improve sampling and inference, leading to faster sample speed, better flexibility of sample queries, and more accurate estimation of inference targets. Our methods are applicable to large models across a range of architectures such as diffusion, autoregressive, and masked-autoencoder models. We demonstrate these findings on applications spanning image and text generation, game-playing, and robotics domains. These insights lead to practical improvements and novel perspectives for efficiently deploying large-scale generative models.
■590 ▼aSchool code: 0212.
■650 4▼aComputer science
■653 ▼aData dimensionality
■653 ▼aModern architectures
■653 ▼aRobotics domains
■690 ▼a0984
■690 ▼a0800
■71020▼aStanford University.
■7730 ▼tDissertations Abstracts International▼g85-11B.
■790 ▼a0212
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161502▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
