본문

서브메뉴

Accelerating Multilinear Maps and Structured Sparse Tensor Kernels
Accelerating Multilinear Maps and Structured Sparse Tensor Kernels
Accelerating Multilinear Maps and Structured Sparse Tensor Kernels

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202104837
ISBN  
9798297600379
DDC  
004
저자명  
Bharadwaj, Vivek.
서명/저자  
Accelerating Multilinear Maps and Structured Sparse Tensor Kernels
발행사항  
[Sl] : University of California, Berkeley, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
184 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-04, Section: B.
주기사항  
Advisor: Demmel, James;Buluc, Aydin.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2025.
초록/해제  
요약Linear maps dominate machine learning and scientific computing workloads today. What about multilinear maps? Just as a linear map with one argument can be represented by a 2D matrix, a D-dimensional multilinear map is represented by a (D + 1)-dimensional tensor. We apply the map by flattening the tensor into a matrix and multiplying it by the Kronecker product of the inputs. When a batch of inputs is provided, this primitive is known as the Matricized-Tensor-Times-Khatri-Rao Product (MTTKRP). Efficient multilinear maps are essential in computational chemistry, multi-way data analysis, and signal processing. Unfortunately, they receive comparatively less interest from theorists and high-performance kernel designers.We optimize the multilinear map in two applications, making contributions that span theory and practical implementation. We first examine equivariant graph neural networks, which use a structured sparse tensor to interact node features with edge features. In response, we design a GPU kernel generator that matches or exceeds the best closed-source implementations for the problem. Our package, OpenEquivariance, provides 5-6x end-to-end speedup for training quantum chemical foundation models. Our focus then shifts to Candecomp / PARAFAC decomposition, a higher-dimensional analogue of the matrix singular value decomposition. Here, we use randomized linear algebra to accelerate the MTTKRP in tall, overdetermined linear least-squares problems, scaling our work to thousands of CPU cores. The remaining chapters detour by adapting this randomized algorithm to sketch tensor trains, structures that originated in quantum mechanical computations. We also design communication-avoiding algorithms for a pair of kernels used in matrix completion and graph attention networks. Our work demonstrates that sustained attention to the multilinear map yields fruit across the computational stack.
일반주제명  
Computer science
일반주제명  
Applied mathematics
키워드  
Graph neural networks
키워드  
Machine learning
키워드  
Multilinearity
키워드  
Tensors
기타저자  
University of California, Berkeley Computer Science
기본자료저록  
Dissertations Abstracts International. 87-04B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359120
■00520260202104837
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798297600379
■035    ▼a(MiAaPQ)AAI32171981
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aBharadwaj,  Vivek.
■24510▼aAccelerating  Multilinear  Maps  and  Structured  Sparse  Tensor  Kernels
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a184  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-04,  Section:  B.
■500    ▼aAdvisor:  Demmel,  James;Buluc,  Aydin.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2025.
■520    ▼aLinear  maps  dominate  machine  learning  and  scientific  computing  workloads  today.  What  about  multilinear  maps?  Just  as  a  linear  map  with  one  argument  can  be  represented  by  a  2D  matrix,  a  D-dimensional  multilinear  map  is  represented  by  a  (D  +  1)-dimensional  tensor.  We  apply  the  map  by  flattening  the  tensor  into  a  matrix  and  multiplying  it  by  the  Kronecker  product  of  the  inputs.  When  a  batch  of  inputs  is  provided,  this  primitive  is  known  as  the  Matricized-Tensor-Times-Khatri-Rao  Product  (MTTKRP).  Efficient  multilinear  maps  are  essential  in  computational  chemistry,  multi-way  data  analysis,  and  signal  processing.  Unfortunately,  they  receive  comparatively  less  interest  from  theorists  and  high-performance  kernel  designers.We  optimize  the  multilinear  map  in  two  applications,  making  contributions  that  span  theory  and  practical  implementation.  We  first  examine  equivariant  graph  neural  networks,  which  use  a  structured  sparse  tensor  to  interact  node  features  with  edge  features.  In  response,  we  design  a  GPU  kernel  generator  that  matches  or  exceeds  the  best  closed-source  implementations  for  the  problem.  Our  package,  OpenEquivariance,  provides  5-6x  end-to-end  speedup  for  training  quantum  chemical  foundation  models.  Our  focus  then  shifts  to  Candecomp  /  PARAFAC  decomposition,  a  higher-dimensional  analogue  of  the  matrix  singular  value  decomposition.  Here,  we  use  randomized  linear  algebra  to  accelerate  the  MTTKRP  in  tall,  overdetermined  linear  least-squares  problems,  scaling  our  work  to  thousands  of  CPU  cores.  The  remaining  chapters  detour  by  adapting  this  randomized  algorithm  to  sketch  tensor  trains,  structures  that  originated  in  quantum  mechanical  computations.  We  also  design  communication-avoiding  algorithms  for  a  pair  of  kernels  used  in  matrix  completion  and  graph  attention  networks.  Our  work  demonstrates  that  sustained  attention  to  the  multilinear  map  yields  fruit  across  the  computational  stack.
■590    ▼aSchool  code:  0028.
■650  4▼aComputer  science
■650  4▼aApplied  mathematics
■653    ▼aGraph  neural  networks
■653    ▼aMachine  learning
■653    ▼aMultilinearity
■653    ▼aTensors
■690    ▼a0984
■690    ▼a0364
■690    ▼a0800
■71020▼aUniversity  of  California,  Berkeley▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g87-04B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359120▼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
    TF17537 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.