본문

서브메뉴

Principles of Uncertainty in Probabilistic Machine Learning
Principles of Uncertainty in Probabilistic Machine Learning
Principles of Uncertainty in Probabilistic Machine Learning

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202104854
ISBN  
9798288814181
DDC  
330
저자명  
Marx, Charles Thomas.
서명/저자  
Principles of Uncertainty in Probabilistic Machine Learning
발행사항  
[Sl] : Stanford University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
117 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-02, Section: B.
주기사항  
Advisor: Ermon, Stefano.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2025.
초록/해제  
요약Reliable uncertainty quantification is fundamental to the safe and effective deployment of machine learning systems in high-stakes settings, where predictions inform decisions ranging from medical diagnoses to infrastructure management and scientific discovery. This dissertation presents a study of probabilistic prediction with a focus on making uncertainty estimates trustworthy by achieving calibration - wherein predicted probabilities align with the empirical frequencies of events, such as a 90% confidence interval including the observed outcome 90% of the time. I propose interventions to improve calibration across the model lifecycle: training objectives to encourage calibration, post-processing methods to correct miscalibration, and online techniques for adaptively preserving calibration during deployment in nonstationary environments. The first part addresses post-hoc recalibration. I introduce modular conformal calibration, a general framework that encompasses and extends existing post-hoc uncertainty quantification techniques such as isotonic regression and conformal prediction. This framework identifies a design space for recalibration procedures and provides finite-sample calibration guarantees for any model recalibrated using these strategies. This allows practitioners to trade off between computational cost, meaningful likelihoods, deterministic behavior, and stronger calibration guarantees. In the second part, I turn to training-time calibration with the goal of encouraging calibration while maintaining sharpness - the degree to which predictions are confident and informative. I propose a class of differentiable calibration measures that serve as regularization objectives, enabling co-optimization of calibration and sharpness during training. These objectives encompass many popular notions of calibration for regression and classification previously enforced only after training, instead incorporating them into standard empirical risk minimization. They also enable task-specific calibration objectives, allowing probabilistic models whose uncertainty estimates are both statistically coherent and aligned with the practical needs of downstream decision-making. The third part investigates calibration under distribution shift, a central challenge in real-world deployments. I consider an online forecasting setting where data may evolve over time or be selected adversarially. Building on Blackwell approachability theory, I develop a general strategy for enforcing calibration guarantees across arbitrary observation sequences under minimal assumptions. This framework supports diverse calibration notions, including distribution and decision calibration, through both oracle-based and computationally tractable algorithms. I further present gradient-based approaches that relax the guarantees while enabling broader applicability. Empirical evaluations demonstrate that these methods maintain calibrated forecasts while achieving vanishing regret with respect to expert predictors. Collectively, this dissertation provides principled strategies for uncertainty estimation with increased flexibility by enforcing many forms of calibration at each stage of model development. This comprehensive approach to calibration across the model lifecycle enables practitioners to tailor uncertainty quantification to their specific applications while reliably informing decisions in high-stakes settings.
일반주제명  
Forecasting
일반주제명  
Decision making
일반주제명  
Computer science
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 87-02B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359241
■00520260202104854
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798288814181
■035    ▼a(MiAaPQ)AAI32200994
■035    ▼a(MiAaPQ)Stanfordsm978sh0523
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a330
■1001  ▼aMarx,  Charles  Thomas.
■24510▼aPrinciples  of  Uncertainty  in  Probabilistic  Machine  Learning
■260    ▼a[Sl]▼bStanford  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a117  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-02,  Section:  B.
■500    ▼aAdvisor:  Ermon,  Stefano.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2025.
■520    ▼aReliable  uncertainty  quantification  is  fundamental  to  the  safe  and  effective  deployment  of  machine  learning  systems  in  high-stakes  settings,  where  predictions  inform  decisions  ranging  from  medical  diagnoses  to  infrastructure  management  and  scientific  discovery.  This  dissertation  presents  a  study  of  probabilistic  prediction  with  a  focus  on  making  uncertainty  estimates  trustworthy  by  achieving  calibration  -  wherein  predicted  probabilities  align  with  the  empirical  frequencies  of  events,  such  as  a  90%  confidence  interval  including  the  observed  outcome  90%  of  the  time.  I  propose  interventions  to  improve  calibration  across  the  model  lifecycle:  training  objectives  to  encourage  calibration,  post-processing  methods  to  correct  miscalibration,  and  online  techniques  for  adaptively  preserving  calibration  during  deployment  in  nonstationary  environments.  The  first  part  addresses  post-hoc  recalibration.  I  introduce  modular  conformal  calibration,  a  general  framework  that  encompasses  and  extends  existing  post-hoc  uncertainty  quantification  techniques  such  as  isotonic  regression  and  conformal  prediction.  This  framework  identifies  a  design  space  for  recalibration  procedures  and  provides  finite-sample  calibration  guarantees  for  any  model  recalibrated  using  these  strategies.  This  allows  practitioners  to  trade  off  between  computational  cost,  meaningful  likelihoods,  deterministic  behavior,  and  stronger  calibration  guarantees.  In  the  second  part,  I  turn  to  training-time  calibration  with  the  goal  of  encouraging  calibration  while  maintaining  sharpness  -  the  degree  to  which  predictions  are  confident  and  informative.  I  propose  a  class  of  differentiable  calibration  measures  that  serve  as  regularization  objectives,  enabling  co-optimization  of  calibration  and  sharpness  during  training.  These  objectives  encompass  many  popular  notions  of  calibration  for  regression  and  classification  previously  enforced  only  after  training,  instead  incorporating  them  into  standard  empirical  risk  minimization.  They  also  enable  task-specific  calibration  objectives,  allowing  probabilistic  models  whose  uncertainty  estimates  are  both  statistically  coherent  and  aligned  with  the  practical  needs  of  downstream  decision-making.  The  third  part  investigates  calibration  under  distribution  shift,  a  central  challenge  in  real-world  deployments.  I  consider  an  online  forecasting  setting  where  data  may  evolve  over  time  or  be  selected  adversarially.  Building  on  Blackwell  approachability  theory,  I  develop  a  general  strategy  for  enforcing  calibration  guarantees  across  arbitrary  observation  sequences  under  minimal  assumptions.  This  framework  supports  diverse  calibration  notions,  including  distribution  and  decision  calibration,  through  both  oracle-based  and  computationally  tractable  algorithms.  I  further  present  gradient-based  approaches  that  relax  the  guarantees  while  enabling  broader  applicability.  Empirical  evaluations  demonstrate  that  these  methods  maintain  calibrated  forecasts  while  achieving  vanishing  regret  with  respect  to  expert  predictors.  Collectively,  this  dissertation  provides  principled  strategies  for  uncertainty  estimation  with  increased  flexibility  by  enforcing  many  forms  of  calibration  at  each  stage  of  model  development.  This  comprehensive  approach  to  calibration  across  the  model  lifecycle  enables  practitioners  to  tailor  uncertainty  quantification  to  their  specific  applications  while  reliably  informing  decisions  in  high-stakes  settings.
■590    ▼aSchool  code:  0212.
■650  4▼aForecasting
■650  4▼aDecision  making
■650  4▼aComputer  science
■690    ▼a0984
■690    ▼a0800
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g87-02B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359241▼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
    TF14912 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.