본문

서브메뉴

Recent Developments in Robust Statistics- [electronic resource]
Recent Developments in Robust Statistics - [electronic resource]
Recent Developments in Robust Statistics- [electronic resource]

상세정보

자료유형  
 학위논문파일 국외
최종처리일시  
20240214101643
ISBN  
9798380366298
DDC  
004
저자명  
Cherapanamjeri, Yeshwanth.
서명/저자  
Recent Developments in Robust Statistics - [electronic resource]
발행사항  
[S.l.]: : University of California, Berkeley., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(84 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
주기사항  
Advisor: Bartlett, Peter.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약The design of statistical estimators robust to outliers has been a mainstay of statistical research through the past six decades. These techniques are even more prescient in the contemporary landscape where large-scale machine learning systems are deployed in increasingly noisy and adaptive environments. In this thesis, we consider the task of building such an estimator for arguably the simplest possible statistical estimation problem - that of mean estimation. There is surprisingly little understanding of the computational and statistical limits of estimation and the trade-offs incurred even for this relatively simple setting. We make progress on this problem along three complementary axes.Our first contribution is a simple algorithmic framework for constructing robust estimators. Our framework allows for a significant speed-up over prior approaches for mean estimation while also allowing for easy extensibility to other statistical estimation tasks where it achieves state-of-the-art performance.Secondly, we investigate the statistical boundaries of mean estimation where we demonstrate the necessary statistical degradation incurred in extremely heavy-tailed scenarios. While prior work showed that estimation could be performed as well as if one had access to Guassian data, we establish that this is no longer true when the data possesses heavier tails. We provide lower bounds which exhibit this degradation and an (efficient) algorithm matching them.Lastly, we consider the stability of these estimators to natural transformations of the data. Inspired by the empirical mean, classical work constructed estimators equivariant to affine transformations. These works, however, lacked the strong quantitative performance of more recent approaches. We demonstrate that such trade-offs are in fact necessary by constructing novel lower bounds for affine-equivariant estimators. We then show that classical estimators are quantitatively deficient even in this restricted class and devise an estimator based on a novel notion of a high-dimensional median which matches the lower bound.
일반주제명  
Computer science.
일반주제명  
Statistics.
키워드  
Machine learning
키워드  
Natural transformations
키워드  
Guassian data
키워드  
Statistical estimation problem
키워드  
Adaptive environments
기타저자  
University of California, Berkeley Computer Science
기본자료저록  
Dissertations Abstracts International. 85-03B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2023      us  |||||||||||||||c||eng  d
■001000016934689
■00520240214101643
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798380366298
■035    ▼a(MiAaPQ)AAI30632930
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aCherapanamjeri,  Yeshwanth.
■24510▼aRecent  Developments  in  Robust  Statistics▼h[electronic  resource]
■260    ▼a[S.l.]:▼bUniversity  of  California,  Berkeley.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(84  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-03,  Section:  B.
■500    ▼aAdvisor:  Bartlett,  Peter.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aThe  design  of  statistical  estimators  robust  to  outliers  has  been  a  mainstay  of  statistical  research  through  the  past  six  decades.  These  techniques  are  even  more  prescient  in  the  contemporary  landscape  where  large-scale  machine  learning  systems  are  deployed  in  increasingly  noisy  and  adaptive  environments.  In  this  thesis,  we  consider  the  task  of  building  such  an  estimator  for  arguably  the  simplest  possible  statistical  estimation  problem  -  that  of  mean  estimation.  There  is  surprisingly  little  understanding  of  the  computational  and  statistical  limits  of  estimation  and  the  trade-offs  incurred  even  for  this  relatively  simple  setting.  We  make  progress  on  this  problem  along  three  complementary  axes.Our  first  contribution  is  a  simple  algorithmic  framework  for  constructing  robust  estimators.  Our  framework  allows  for  a  significant  speed-up  over  prior  approaches  for  mean  estimation  while  also  allowing  for  easy  extensibility  to  other  statistical  estimation  tasks  where  it  achieves  state-of-the-art  performance.Secondly,  we  investigate  the  statistical  boundaries  of  mean  estimation  where  we  demonstrate  the  necessary  statistical  degradation  incurred  in  extremely  heavy-tailed  scenarios.  While  prior  work  showed  that  estimation  could  be  performed  as  well  as  if  one  had  access  to  Guassian  data,  we  establish  that  this  is  no  longer  true  when  the  data  possesses  heavier  tails.  We  provide  lower  bounds  which  exhibit  this  degradation  and  an  (efficient)  algorithm  matching  them.Lastly,  we  consider  the  stability  of  these  estimators  to  natural  transformations  of  the  data.  Inspired  by  the  empirical  mean,  classical  work  constructed  estimators  equivariant  to  affine  transformations.  These  works,  however,  lacked  the  strong  quantitative  performance  of  more  recent  approaches.  We  demonstrate  that  such  trade-offs  are  in  fact  necessary  by  constructing  novel  lower  bounds  for  affine-equivariant  estimators.  We  then  show  that  classical  estimators  are  quantitatively  deficient  even  in  this  restricted  class  and  devise  an  estimator  based  on  a  novel  notion  of  a  high-dimensional  median  which  matches  the  lower  bound.
■590    ▼aSchool  code:  0028.
■650  4▼aComputer  science.
■650  4▼aStatistics.
■653    ▼aMachine  learning
■653    ▼aNatural  transformations
■653    ▼aGuassian  data
■653    ▼aStatistical  estimation  problem
■653    ▼aAdaptive  environments
■690    ▼a0984
■690    ▼a0463
■71020▼aUniversity  of  California,  Berkeley▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g85-03B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16934689▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

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
    TF06426 전자도서 마이폴더 부재도서신고 비도서대출신청

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

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.