본문

서브메뉴

Granular Feedback Merits Sophisticated Aggregation
Granular Feedback Merits Sophisticated Aggregation
Granular Feedback Merits Sophisticated Aggregation

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105626
ISBN  
9798265428820
DDC  
519.7
저자명  
Kagrecha, Anmol.
서명/저자  
Granular Feedback Merits Sophisticated Aggregation
발행사항  
[Sl] : Stanford University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
61 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Van Roy, Benjamin.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2025.
초록/해제  
요약Human feedback is increasingly used across diverse applications like training AI models, developing recommender systems, and measuring public opinion - with granular feedback often being preferred over binary feedback for its greater informativeness. While it is easy to accurately estimate a population's distribution of feedback given feedback from a large number of individuals, cost constraints typically necessitate using smaller groups. A simple method to approximate the population distribution is regularized averaging: compute the empirical distribution and regularize it toward a prior. Can we do better? As we will discuss, the answer to this question depends on feedback granularity.Suppose one wants to predict a population's distribution of feedback using feedback from a limited number of individuals. We show that, as feedback granularity increases, one can substantially improve upon predictions of regularized averaging by combining individuals' feedback in ways more sophisticated than regularized averaging.Our empirical analysis using questions on social attitudes confirms this pattern. In particular, with binary feedback, sophistication barely reduces the number of individuals required to attain a fixed level of performance. By contrast, with five-point feedback, sophisticated methods match the performance of regularized averaging with about half as many individuals.Besides discussing how the advantage of sophisticated aggregation methods varies with granularity, we also discuss two results. First, we discuss how sophisticated aggregation methods can improve a typical pipeline for training large language models. Second, we demonstrate experimentally that if one has interacted sufficiently many times with a set of individuals, then one could collect feedback from only a subset of these individuals while maintaining equivalent performance. Combined with our main result that sophisticated aggregation methods provide a larger advantage for granular feedback, this subset selection capability implies that the joint use of sophisticated aggregation and selection can substantially outperform the combination of regularized averaging and random selection when feedback is granular. A major part of this dissertation is adapted from a recent preprint (Kagrecha et al., 2025) authored by Anmol Kagrecha, Henrik Marklund, Potsawee Manakul, Richard Zeckhauser, and Benjamin Van Roy.
일반주제명  
Optimization techniques
일반주제명  
Families & family life
일반주제명  
Attitudes
일반주제명  
Abortion
일반주제명  
Crowdsourcing
일반주제명  
Individual & family studies
일반주제명  
Web studies
일반주제명  
Obstetrics
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017360839
■00520260202105626
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798265428820
■035    ▼a(MiAaPQ)AAI32316560
■035    ▼a(MiAaPQ)Stanfordpd147dc7682
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a519.7
■1001  ▼aKagrecha,  Anmol.
■24510▼aGranular  Feedback  Merits  Sophisticated  Aggregation
■260    ▼a[Sl]▼bStanford  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a61  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Van  Roy,  Benjamin.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2025.
■520    ▼aHuman  feedback  is  increasingly  used  across  diverse  applications  like  training  AI  models,  developing  recommender  systems,  and  measuring  public  opinion  -  with  granular  feedback  often  being  preferred  over  binary  feedback  for  its  greater  informativeness.  While  it  is  easy  to  accurately  estimate  a  population's  distribution  of  feedback  given  feedback  from  a  large  number  of  individuals,  cost  constraints  typically  necessitate  using  smaller  groups.  A  simple  method  to  approximate  the  population  distribution  is  regularized  averaging:  compute  the  empirical  distribution  and  regularize  it  toward  a  prior.  Can  we  do  better?  As  we  will  discuss,  the  answer  to  this  question  depends  on  feedback  granularity.Suppose  one  wants  to  predict  a  population's  distribution  of  feedback  using  feedback  from  a  limited  number  of  individuals.  We  show  that,  as  feedback  granularity  increases,  one  can  substantially  improve  upon  predictions  of  regularized  averaging  by  combining  individuals'  feedback  in  ways  more  sophisticated  than  regularized  averaging.Our  empirical  analysis  using  questions  on  social  attitudes  confirms  this  pattern.  In  particular,  with  binary  feedback,  sophistication  barely  reduces  the  number  of  individuals  required  to  attain  a  fixed  level  of  performance.  By  contrast,  with  five-point  feedback,  sophisticated  methods  match  the  performance  of  regularized  averaging  with  about  half  as  many  individuals.Besides  discussing  how  the  advantage  of  sophisticated  aggregation  methods  varies  with  granularity,  we  also  discuss  two  results.  First,  we  discuss  how  sophisticated  aggregation  methods  can  improve  a  typical  pipeline  for  training  large  language  models.  Second,  we  demonstrate  experimentally  that  if  one  has  interacted  sufficiently  many  times  with  a  set  of  individuals,  then  one  could  collect  feedback  from  only  a  subset  of  these  individuals  while  maintaining  equivalent  performance.  Combined  with  our  main  result  that  sophisticated  aggregation  methods  provide  a  larger  advantage  for  granular  feedback,  this  subset  selection  capability  implies  that  the  joint  use  of  sophisticated  aggregation  and  selection  can  substantially  outperform  the  combination  of  regularized  averaging  and  random  selection  when  feedback  is  granular.  A  major  part  of  this  dissertation  is  adapted  from  a  recent  preprint  (Kagrecha  et  al.,  2025)  authored  by  Anmol  Kagrecha,  Henrik  Marklund,  Potsawee  Manakul,  Richard  Zeckhauser,  and  Benjamin  Van  Roy.
■590    ▼aSchool  code:  0212.
■650  4▼aOptimization  techniques
■650  4▼aFamilies  &  family  life
■650  4▼aAttitudes
■650  4▼aAbortion
■650  4▼aCrowdsourcing
■650  4▼aIndividual  &  family  studies
■650  4▼aWeb  studies
■650  4▼aObstetrics
■690    ▼a0628
■690    ▼a0646
■690    ▼a0380
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360839▼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
    TF18381 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.