본문

서브메뉴

Phase Transitions in Inference- [electronic resource]
Phase Transitions in Inference - [electronic resource]
Phase Transitions in Inference- [electronic resource]

Detailed Information

자료유형  
 학위논문파일 국외
최종처리일시  
20240214101644
ISBN  
9798380366564
DDC  
004
저자명  
Mohanty, Sidhanth.
서명/저자  
Phase Transitions in Inference - [electronic resource]
발행사항  
[S.l.]: : University of California, Berkeley., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(306 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
주기사항  
Advisor: Raghavendra, Prasad.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약What makes an algorithmic problem easy or hard? Many general algorithmic techniques arising from decades of research, along with the theory of NP-completeness based on reductions between hard problems, offers a good answer for problems where the input is ``worst-case''.However, this theory has very little to say when the input is random, and comprises of independent samples, as is frequently the case for problems in statistics. Statistical problems seemingly go through abrupt phase transitions in complexity, from hard to easy once the number of samples crosses a threshold. Understanding this boundary between ``hard'' and ``easy'' for statistical problems is still in nascent stages.This thesis comprises recent progress in understanding these phase transitions from the lens of semidefinite programming.
일반주제명  
Computer science.
일반주제명  
Computer engineering.
키워드  
Algorithmic techniques
키워드  
Algorithmic problem
키워드  
Semidefinite programming
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
■001000016934708
■00520240214101644
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798380366564
■035    ▼a(MiAaPQ)AAI30633323
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aMohanty,  Sidhanth.
■24510▼aPhase  Transitions  in  Inference▼h[electronic  resource]
■260    ▼a[S.l.]:▼bUniversity  of  California,  Berkeley.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(306  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-03,  Section:  B.
■500    ▼aAdvisor:  Raghavendra,  Prasad.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aWhat  makes  an  algorithmic  problem  easy  or  hard?    Many  general  algorithmic  techniques  arising  from  decades  of  research,  along  with  the  theory  of  NP-completeness  based  on  reductions  between  hard  problems,  offers  a  good  answer  for  problems  where  the  input  is  ``worst-case''.However,  this  theory  has  very  little  to  say  when  the  input  is  random,  and  comprises  of  independent  samples,  as  is  frequently  the  case  for  problems  in  statistics.    Statistical  problems  seemingly  go  through  abrupt  phase  transitions  in  complexity,  from  hard  to  easy  once  the  number  of  samples  crosses  a  threshold.    Understanding  this  boundary  between  ``hard''  and  ``easy''  for  statistical  problems  is  still  in  nascent  stages.This  thesis  comprises  recent  progress  in  understanding  these  phase  transitions  from  the  lens  of  semidefinite  programming.
■590    ▼aSchool  code:  0028.
■650  4▼aComputer  science.
■650  4▼aComputer  engineering.
■653    ▼aAlgorithmic  techniques
■653    ▼aAlgorithmic  problem
■653    ▼aSemidefinite  programming
■690    ▼a0984
■690    ▼a0464
■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=T16934708▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

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
    TF08091 전자도서 My Folder 부재도서신고 비도서대출신청

    * 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.