본문

서브메뉴

Mathematical Statistics in 2025
Mathematical Statistics in 2025
Mathematical Statistics in 2025

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202104854
ISBN  
9798288816659
DDC  
330
저자명  
Dey, Apratim.
서명/저자  
Mathematical Statistics in 2025
발행사항  
[Sl] : Stanford University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
135 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
주기사항  
Advisor: Donoho, David Leigh.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2025.
초록/해제  
요약Over a century has passed since R. A. Fisher laid the mathematical foundations of modern statistical theory. The intervening decades have produced a steady stream of advances that have deepened our understanding of the notions of inference, optimality, and uncertainty. As recently as fifteen years ago, a doctoral dissertation in statistics could still focus almost exclusively on problems internal to the discipline, and that would be completely uncontroversial to do so. However, the landscape in 2025 is markedly different. Rapid advances in digital technology and computing power now shape virtually every sphere of human activity. Vast investments in hardware and software champion scale and performance, often at the expense of foundational scientific insight. In such an environment, the distinctive role of statistics can appear diminished, and it is natural to ask what the field still contributes amid data-driven benchmarks, machine-learning models, and algorithmic decision-making. This dissertation contends that the answer lies precisely in the classical principles of mathematical statistics. Far from being obsolete, these principles provide the rigorous framework needed to harness modern technology effectively. To demonstrate this claim, the thesis examines two problems that originate outside the traditional statistical canon: Chapter 1 addresses a question in signal processing, while Chapter 3 tackles an issue in empirical machine learning. The chapters may seem to confront disparate problems, yet they are strung together by a common thread. In both settings, classical statistical theory proves indispensable, offering clarity, structure, and crucially, a path to provable optimality unattainable through brute-force computation or indiscriminate data accumulation. The problems may have evolved, but the guiding principles have not. By returning to the foundations of mathematical statistics we can confront contemporary challenges without surrendering to blind reliance on data and compute. The enduring lesson is straightforward: rigorous statistical thinking is more relevant, and more necessary, than ever.
일반주제명  
Sparsity
일반주제명  
Software quality
일반주제명  
Spectrum analysis
일반주제명  
Success
일반주제명  
Signal processing
일반주제명  
Phase transitions
일반주제명  
Convex analysis
일반주제명  
Wearable computers
일반주제명  
Statistics
일반주제명  
Applied mathematics
일반주제명  
Mathematics
키워드  
Modern statistical theory
키워드  
Machine-learning models
키워드  
Algorithmic decision-making
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 87-01B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359243
■00520260202104854
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798288816659
■035    ▼a(MiAaPQ)AAI32200998
■035    ▼a(MiAaPQ)Stanfordtj135bv3146
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a330
■1001  ▼aDey,  Apratim.
■24510▼aMathematical  Statistics  in  2025
■260    ▼a[Sl]▼bStanford  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a135  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-01,  Section:  B.
■500    ▼aAdvisor:  Donoho,  David  Leigh.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2025.
■520    ▼aOver  a  century  has  passed  since  R.  A.  Fisher  laid  the  mathematical  foundations  of  modern  statistical  theory.  The  intervening  decades  have  produced  a  steady  stream  of  advances  that  have  deepened  our  understanding  of  the  notions  of  inference,  optimality,  and  uncertainty.  As  recently  as  fifteen  years  ago,  a  doctoral  dissertation  in  statistics  could  still  focus  almost  exclusively  on  problems  internal  to  the  discipline,  and  that  would  be  completely  uncontroversial  to  do  so.  However,  the  landscape  in  2025  is  markedly  different.  Rapid  advances  in  digital  technology  and  computing  power  now  shape  virtually  every  sphere  of  human  activity.  Vast  investments  in  hardware  and  software  champion  scale  and  performance,  often  at  the  expense  of  foundational  scientific  insight.  In  such  an  environment,  the  distinctive  role  of  statistics  can  appear  diminished,  and  it  is  natural  to  ask  what  the  field  still  contributes  amid  data-driven  benchmarks,  machine-learning  models,  and  algorithmic  decision-making.  This  dissertation  contends  that  the  answer  lies  precisely  in  the  classical  principles  of  mathematical  statistics.  Far  from  being  obsolete,  these  principles  provide  the  rigorous  framework  needed  to  harness  modern  technology  effectively.  To  demonstrate  this  claim,  the  thesis  examines  two  problems  that  originate  outside  the  traditional  statistical  canon:  Chapter  1  addresses  a  question  in  signal  processing,  while  Chapter  3  tackles  an  issue  in  empirical  machine  learning.  The  chapters  may  seem  to  confront  disparate  problems,  yet  they  are  strung  together  by  a  common  thread.  In  both  settings,  classical  statistical  theory  proves  indispensable,  offering  clarity,  structure,  and  crucially,  a  path  to  provable  optimality  unattainable  through  brute-force  computation  or  indiscriminate  data  accumulation.  The  problems  may  have  evolved,  but  the  guiding  principles  have  not.  By  returning  to  the  foundations  of  mathematical  statistics  we  can  confront  contemporary  challenges  without  surrendering  to  blind  reliance  on  data  and  compute.  The  enduring  lesson  is  straightforward:  rigorous  statistical  thinking  is  more  relevant,  and  more  necessary,  than  ever.
■590    ▼aSchool  code:  0212.
■650  4▼aSparsity
■650  4▼aSoftware  quality
■650  4▼aSpectrum  analysis
■650  4▼aSuccess
■650  4▼aSignal  processing
■650  4▼aPhase  transitions
■650  4▼aConvex  analysis
■650  4▼aWearable  computers
■650  4▼aStatistics
■650  4▼aApplied  mathematics
■650  4▼aMathematics
■653    ▼aModern  statistical  theory
■653    ▼aMachine-learning  models
■653    ▼aAlgorithmic  decision-making
■690    ▼a0364
■690    ▼a0463
■690    ▼a0405
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g87-01B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359243▼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
    TF14914 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.