본문

서브메뉴

Statistical Physics of Gradient Descent in High-Dimensions: From Coherent Ising Machines to Neural Networks
Statistical Physics of Gradient Descent in High-Dimensions: From Coherent Ising Machines t...
Statistical Physics of Gradient Descent in High-Dimensions: From Coherent Ising Machines to Neural Networks

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202105626
ISBN  
9798265428004
DDC  
530.13
저자명  
Yamamura, Atsushi.
서명/저자  
Statistical Physics of Gradient Descent in High-Dimensions: From Coherent Ising Machines to Neural Networks
발행사항  
[Sl] : Stanford University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
183 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Ganguli, Surya;Mabuchi, Hideo.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2025.
초록/해제  
요약Gradient descent and its variants are widely employed in optimization and machine learning tasks. A fundamental understanding of their behavior in high-dimensional loss or energy landscapes is essential for improving performance and efficiency. In the first part of this dissertation, we analyze the optimization dynamics of coherent Ising machines (CIMs)-optical recurrent neural networks designed to solve combinatorial optimization problems. By investigating their behavior on random combinatorial instances through statistical physics methods, we identify distinct phase transitions in the energy landscape of CIMs, from flat to rough to rigid. These transitions significantly influence gradient descent dynamics, providing valuable insights into optimal hyperparameter tuning for enhanced CIM performance.In the second part, we explore the dynamics of stochastic gradient descent (SGD) in deep neural networks, focusing on the fundamental question of why these networks exhibit remarkable generalization capabilities. We demonstrate that the stochastic noise intrinsic to SGD possesses a structured form determined by the architectural symmetries of neural networks. This structured noise guides SGD dynamics toward specific subsets of parameter space characterized by "simpler" functions, thereby mitigating overfitting and enhancing the model's ability to generalize to unseen data.
일반주제명  
Brownian motion
일반주제명  
Semiconductors
일반주제명  
Lasers
일반주제명  
Neural networks
일반주제명  
Symmetry
일반주제명  
Phase transitions
일반주제명  
Statistical physics
일반주제명  
Connectivity
일반주제명  
Eigenvalues
일반주제명  
Energy
일반주제명  
Traveling salesman problem
일반주제명  
Eigenvectors
일반주제명  
Geometry
일반주제명  
Mathematics
일반주제명  
Optics
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
■001000017360838
■00520260202105626
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798265428004
■035    ▼a(MiAaPQ)AAI32316558
■035    ▼a(MiAaPQ)Stanfordnx340sz2444
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a530.13
■1001  ▼aYamamura,  Atsushi.
■24510▼aStatistical  Physics  of  Gradient  Descent  in  High-Dimensions:  From  Coherent  Ising  Machines  to  Neural  Networks
■260    ▼a[Sl]▼bStanford  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a183  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Ganguli,  Surya;Mabuchi,  Hideo.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2025.
■520    ▼aGradient  descent  and  its  variants  are  widely  employed  in  optimization  and  machine  learning  tasks.  A  fundamental  understanding  of  their  behavior  in  high-dimensional  loss  or  energy  landscapes  is  essential  for  improving  performance  and  efficiency.  In  the  first  part  of  this  dissertation,  we  analyze  the  optimization  dynamics  of  coherent  Ising  machines  (CIMs)-optical  recurrent  neural  networks  designed  to  solve  combinatorial  optimization  problems.  By  investigating  their  behavior  on  random  combinatorial  instances  through  statistical  physics  methods,  we  identify  distinct  phase  transitions  in  the  energy  landscape  of  CIMs,  from  flat  to  rough  to  rigid.  These  transitions  significantly  influence  gradient  descent  dynamics,  providing  valuable  insights  into  optimal  hyperparameter  tuning  for  enhanced  CIM  performance.In  the  second  part,  we  explore  the  dynamics  of  stochastic  gradient  descent  (SGD)  in  deep  neural  networks,  focusing  on  the  fundamental  question  of  why  these  networks  exhibit  remarkable  generalization  capabilities.  We  demonstrate  that  the  stochastic  noise  intrinsic  to  SGD  possesses  a  structured  form  determined  by  the  architectural  symmetries  of  neural  networks.  This  structured  noise  guides  SGD  dynamics  toward  specific  subsets  of  parameter  space  characterized  by  "simpler"  functions,  thereby  mitigating  overfitting  and  enhancing  the  model's  ability  to  generalize  to  unseen  data.
■590    ▼aSchool  code:  0212.
■650  4▼aBrownian  motion
■650  4▼aSemiconductors
■650  4▼aLasers
■650  4▼aNeural  networks
■650  4▼aSymmetry
■650  4▼aPhase  transitions
■650  4▼aStatistical  physics
■650  4▼aConnectivity
■650  4▼aEigenvalues
■650  4▼aEnergy
■650  4▼aTraveling  salesman  problem
■650  4▼aEigenvectors
■650  4▼aGeometry
■650  4▼aMathematics
■650  4▼aOptics
■690    ▼a0791
■690    ▼a0217
■690    ▼a0800
■690    ▼a0405
■690    ▼a0796
■690    ▼a0752
■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=T17360838▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

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
    TF18380 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * 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.