본문

서브메뉴

Algorithms for Robust Learning, Gradient Flows, and Diffusion Generation of Rare Events
Algorithms for Robust Learning, Gradient Flows, and Diffusion Generation of Rare Events
Algorithms for Robust Learning, Gradient Flows, and Diffusion Generation of Rare Events

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152747
ISBN  
9798342107211
DDC  
510
저자명  
Hua, Xinru.
서명/저자  
Algorithms for Robust Learning, Gradient Flows, and Diffusion Generation of Rare Events
발행사항  
[Sl] : Stanford University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
125 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-04, Section: B.
주기사항  
Advisor: Mancilla, Jose Blanchet;Ma, Tengyu.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2024.
초록/해제  
요약As machine learning systems become an integral part of our daily lives, particularly with the remarkable advancements of foundation models, we must assess their trustworthiness, fairness, and also exploring methods to improve these crucial aspects. This dissertation explores the measurement and enhancement of a machine learning model's performance, robustness, and fairness. Furthermore, we explore the design and deployment of these systems in novel application fields, with these metrics as crucial objectives.This thesis aims to make machine learning more trustable and powerful in general. The first topic is on evaluating the robustness and fairness of machine learning models and strategies to enhance them. Our method combines distributionally robust optimization (DRO) and human imperceptible adversarial attacks to simultaneously improve both model robustness and fairness. By analyzing the robustness and fairness of the machine learning systems, we intuitively bring machine perception closer to human perception. In addition to robustness and fairness, we study the gradient flow method to alleviate data scarcity problem and improve classification systems' performance in few-shot learning settings. We prove the gradient flow method converge globally and the downstream transfer learning tasks demonstrate its ability to generate useful data samples. Lastly, we focus on an innovative application of machine learning algorithms in the field of material science. Specifically, we design machine learning systems to accelerate the sampling of rare events in molecular simulations. Our approach yields substantial speed improvements compared to traditional sampling methods, along with robust estimations of the probability of these rare events.Throughout the thesis, we demonstrate that machine learning can be improved in many aspects, including fairness and robustness. We also showcase its power in traditional applications, such as mechanical simulations. Future work will extend these systems to tackle more complex and higher-dimensional challenges. With the ongoing efforts, the thesis contributes to the development of more reliable and potent machine learning systems.
일반주제명  
Sample size
일반주제명  
Deep learning
일반주제명  
Neural networks
일반주제명  
Design
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 86-04B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017163742
■00520250211152747
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798342107211
■035    ▼a(MiAaPQ)AAI31520314
■035    ▼a(MiAaPQ)Stanfordsz944xc0403
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a510
■1001  ▼aHua,  Xinru.
■24510▼aAlgorithms  for  Robust  Learning,  Gradient  Flows,  and  Diffusion  Generation  of  Rare  Events
■260    ▼a[Sl]▼bStanford  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a125  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-04,  Section:  B.
■500    ▼aAdvisor:  Mancilla,  Jose  Blanchet;Ma,  Tengyu.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2024.
■520    ▼aAs  machine  learning  systems  become  an  integral  part  of  our  daily  lives,  particularly  with  the  remarkable  advancements  of  foundation  models,  we  must  assess  their  trustworthiness,  fairness,  and  also  exploring  methods  to  improve  these  crucial  aspects.  This  dissertation  explores  the  measurement  and  enhancement  of  a  machine  learning  model's  performance,  robustness,  and  fairness.  Furthermore,  we  explore  the  design  and  deployment  of  these  systems  in  novel  application  fields,  with  these  metrics  as  crucial  objectives.This  thesis  aims  to  make  machine  learning  more  trustable  and  powerful  in  general.  The  first  topic  is  on  evaluating  the  robustness  and  fairness  of  machine  learning  models  and  strategies  to  enhance  them.  Our  method  combines  distributionally  robust  optimization  (DRO)  and  human  imperceptible  adversarial  attacks  to  simultaneously  improve  both  model  robustness  and  fairness.  By  analyzing  the  robustness  and  fairness  of  the  machine  learning  systems,  we  intuitively  bring  machine  perception  closer  to  human  perception.  In  addition  to  robustness  and  fairness,  we  study  the  gradient  flow  method  to  alleviate  data  scarcity  problem  and  improve  classification  systems'  performance  in  few-shot  learning  settings.  We  prove  the  gradient  flow  method  converge  globally  and  the  downstream  transfer  learning  tasks  demonstrate  its  ability  to  generate  useful  data  samples.  Lastly,  we  focus  on  an  innovative  application  of  machine  learning  algorithms  in  the  field  of  material  science.  Specifically,  we  design  machine  learning  systems  to  accelerate  the  sampling  of  rare  events  in  molecular  simulations.  Our  approach  yields  substantial  speed  improvements  compared  to  traditional  sampling  methods,  along  with  robust  estimations  of  the  probability  of  these  rare  events.Throughout  the  thesis,  we  demonstrate  that  machine  learning  can  be  improved  in  many  aspects,  including  fairness  and  robustness.  We  also  showcase  its  power  in  traditional  applications,  such  as  mechanical  simulations.  Future  work  will  extend  these  systems  to  tackle  more  complex  and  higher-dimensional  challenges.  With  the  ongoing  efforts,  the  thesis  contributes  to  the  development  of  more  reliable  and  potent  machine  learning  systems.
■590    ▼aSchool  code:  0212.
■650  4▼aSample  size
■650  4▼aDeep  learning
■650  4▼aNeural  networks
■650  4▼aDesign
■690    ▼a0389
■690    ▼a0800
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g86-04B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163742▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF09732 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.