본문

서브메뉴

Trustworthiness : Revisiting the Foundations of Machine Learning
Trustworthiness : Revisiting the Foundations of Machine Learning
Trustworthiness : Revisiting the Foundations of Machine Learning

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20250211152121
ISBN  
9798384341949
DDC  
616
저자명  
Hu, Lunjia.
서명/저자  
Trustworthiness : Revisiting the Foundations of Machine Learning
발행사항  
[Sl] : Stanford University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
239 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-03, Section: A.
주기사항  
Advisor: Charikar, Moses;Reingold, Omer.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2024.
초록/해제  
요약As we deploy machine learning models in more and more complex and critical tasks, can we trust that these models will work as intended in real-world settings? For example, a doctor might use a machine learning model to evaluate patients' risk of developing specific diseases and make consequential treatment decisions based on the model's predictions. There are significant barriers to building such trust-machine learning predictions are frustratingly inscrutable, concerns about unfair treatment of minority groups abound, and strong performance in idealized settings often breaks down on realworld data. To be trustworthy, a model must provide guarantees beyond the standard objectives of accuracy and loss minimization (i.e., minimizing a function that penalizes overall error). A trustworthy model should give interpretable explanations for its predictions, should be fair to patients from protected subpopulations, and should be robuston real-world data that does not satisfy idealized assumptions. These considerations have motivated a rapid growth of research on trustworthy machine learning.This dissertation presents my research that develops new mathematical theories to address fundamental problems in trustworthy machine learning, and also conversely, applies the insights from trustworthiness to discover new foundational theories for machine learning, computer science, and statistics.My research presented in this dissertation highlights the symbiotic relationship between studying practical issues of trustworthiness and building the theoretical foundations of machine learning. On one hand, trustworthiness notions exhibit varying levels of complexity and subtlety, needing mathematical sophistication to avoid ambiguity and provide principled guidance. Historically, theoretical computer science has achieved great success in formalizing seemingly vague concepts such as secrecy, rationality, learning, and privacy. Following this tradition, my research has developed new theories to answer pressing questions in trustworthy machine learning that are beyond the reach of empirical research alone. Chapter 1 presents a theory of calibration that has enabled an open-source Python package [B lasiok and Nakkiran, 2023] solving problems that caused common confusion and frustration in previous research. On the other hand, the versatility of trustworthiness considerations is a iv vibrant source of inspiration for new foundational theories. Several lines of my research have uncovered surprisingly richer theories than previously known for classic problems in machine learning and statistics: Chapter 2 presents new sample complexity theories generalizing the classic VC theory, whereas Chapter 3 presents new theories of omnipredictionwhich allows efficient training of a single prediction model that is easily adaptable to optimize a rich family of loss functions potentially with varying constraints.
일반주제명  
Cardiovascular disease
일반주제명  
Probability
일반주제명  
Computer science
일반주제명  
Distance learning
일반주제명  
Neural networks
일반주제명  
Educational technology
일반주제명  
Medicine
일반주제명  
Public health
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 86-03A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017162994
■00520250211152121
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384341949
■035    ▼a(MiAaPQ)AAI31460394
■035    ▼a(MiAaPQ)Stanfordzy428st6966
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a616
■1001  ▼aHu,  Lunjia.
■24510▼aTrustworthiness  :  Revisiting  the  Foundations  of  Machine  Learning
■260    ▼a[Sl]▼bStanford  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a239  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-03,  Section:  A.
■500    ▼aAdvisor:  Charikar,  Moses;Reingold,  Omer.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2024.
■520    ▼aAs  we  deploy  machine  learning  models  in  more  and  more  complex  and  critical  tasks,  can  we  trust  that  these  models  will  work  as  intended  in  real-world  settings?  For  example,  a  doctor  might  use  a  machine  learning  model  to  evaluate  patients'  risk  of  developing  specific  diseases  and  make  consequential  treatment  decisions  based  on  the  model's  predictions.  There  are  significant  barriers  to  building  such  trust-machine  learning  predictions  are  frustratingly  inscrutable,  concerns  about  unfair  treatment  of  minority  groups  abound,  and  strong  performance  in  idealized  settings  often  breaks  down  on  realworld  data.  To  be  trustworthy,  a  model  must  provide  guarantees  beyond  the  standard  objectives  of  accuracy  and  loss  minimization  (i.e.,  minimizing  a  function  that  penalizes  overall  error).  A  trustworthy  model  should  give  interpretable  explanations  for  its  predictions,  should  be  fair  to  patients  from  protected  subpopulations,  and  should  be  robuston  real-world  data  that  does  not  satisfy  idealized  assumptions.  These  considerations  have  motivated  a  rapid  growth  of  research  on  trustworthy  machine  learning.This  dissertation  presents  my  research  that  develops  new  mathematical  theories  to  address  fundamental  problems  in  trustworthy  machine  learning,  and  also  conversely,  applies  the  insights  from  trustworthiness  to  discover  new  foundational  theories  for  machine  learning,  computer  science,  and  statistics.My  research  presented  in  this  dissertation  highlights  the  symbiotic  relationship  between  studying  practical  issues  of  trustworthiness  and  building  the  theoretical  foundations  of  machine  learning.  On  one  hand,  trustworthiness  notions  exhibit  varying  levels  of  complexity  and  subtlety,  needing  mathematical  sophistication  to  avoid  ambiguity  and  provide  principled  guidance.  Historically,  theoretical  computer  science  has  achieved  great  success  in  formalizing  seemingly  vague  concepts  such  as  secrecy,  rationality,  learning,  and  privacy.  Following  this  tradition,  my  research  has  developed  new  theories  to  answer  pressing  questions  in  trustworthy  machine  learning  that  are  beyond  the  reach  of  empirical  research  alone.  Chapter  1  presents  a  theory  of  calibration  that  has  enabled  an  open-source  Python  package  [B  lasiok  and  Nakkiran,  2023]  solving  problems  that  caused  common  confusion  and  frustration  in  previous  research.  On  the  other  hand,  the  versatility  of  trustworthiness  considerations  is  a  iv  vibrant  source  of  inspiration  for  new  foundational  theories.  Several  lines  of  my  research  have  uncovered  surprisingly  richer  theories  than  previously  known  for  classic  problems  in  machine  learning  and  statistics:  Chapter  2  presents  new  sample  complexity  theories  generalizing  the  classic  VC  theory,  whereas  Chapter  3  presents  new  theories  of  omnipredictionwhich  allows  efficient  training  of  a  single  prediction  model  that  is  easily  adaptable  to  optimize  a  rich  family  of  loss  functions  potentially  with  varying  constraints.
■590    ▼aSchool  code:  0212.
■650  4▼aCardiovascular  disease
■650  4▼aProbability
■650  4▼aComputer  science
■650  4▼aDistance  learning
■650  4▼aNeural  networks
■650  4▼aEducational  technology
■650  4▼aMedicine
■650  4▼aPublic  health
■690    ▼a0984
■690    ▼a0800
■690    ▼a0710
■690    ▼a0564
■690    ▼a0573
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g86-03A.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162994▼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

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF11122 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.