Joint Mathematics Meetings AMS Special Session

Current as of Saturday, January 18, 2025 03:30:05

• Program
• ·
• Deadlines
• ·
• Timetable
• ·
• Inquiries: meet@ams.org

2025 Joint Mathematics Meetings (JMM 2025)

• Seattle Convention Center and the Sheraton Grand Seattle, Seattle, WA
• January 8-11, 2025 (Wednesday - Saturday)
• Meeting #1203

Associate Secretary for the AMS Scientific Program:

Brian D. Boe, brian@math.uga.edu

AMS Special Session on Geometry and Machine Learning

• Saturday January 11, 2025, 8:00 a.m.-12:00 p.m.
  AMS Special Session on Geometry and Machine Learning, I
  Innovative research is being done at the intersection of geometry and machine learning, enriching both fields. Methods and techniques from geometry are being used to better understand the mathematical foundations of machine learning, and new tools and techniques from machine learning are being used to shed light on questions in geometry. This session will support the growing community of researchers working at this intersection.
  613, Seattle Convention Center Arch at 705 Pike
  Organizers:
  Tingting Tang, San Diego State University ttang2@sdsu.edu
  Yang-Hui He, City, University of London
  Fabian Ruehle, Northeastern University
  Yaim Cooper, University of Notre Dame
  

  • 8:00 a.m.
    Mathematical Foundations of AI: learning compositionally sparse functions
    Tomaso Poggio*, MIT, CBMM
    (1203-68-45056)
  • 9:00 a.m.
    Harmonic $1$-forms on real loci of Calabi-Yau manifolds
    Michael R. Douglas*, Harvard / Stony Brook
    (1203-32-42246)
  • 10:00 a.m.
    Regularized SGD Secretly Compresses Your Neural Network
    Tomer Galanti*, Texas A&M University
    (1203-68-44371)
  • 11:00 a.m.
    A machine learning approach to resolution of singularities
    Gergely Berczi*, Aarhus University
    Honglu Fan, University of Geneva
    Mingcong Zeng, Aarhus University
    (1203-14-45271)
• Saturday January 11, 2025, 1:00 p.m.-6:00 p.m.
  AMS Special Session on Geometry and Machine Learning, II
  Innovative research is being done at the intersection of geometry and machine learning, enriching both fields. Methods and techniques from geometry are being used to better understand the mathematical foundations of machine learning, and new tools and techniques from machine learning are being used to shed light on questions in geometry. This session will support the growing community of researchers working at this intersection.
  613, Seattle Convention Center Arch at 705 Pike
  Organizers:
  Tingting Tang, San Diego State University ttang2@sdsu.edu
  Yang-Hui He, City, University of London
  Fabian Ruehle, Northeastern University
  Yaim Cooper, University of Notre Dame
  

  • 1:00 p.m.
    The Real Tropical Geometry of Neural Networks for Binary Classification
    Marie-Charlotte Brandenburg, KTH
    Georg Loho, University of Twente
    Guido Francisco Montufar*, University of California, Los Angeles
    (1203-68-42438)
  • 2:00 p.m.
    Searching for black swans
    Sergei Gukov*, California Institute of Technology
    (1203-90-44679)
  • 3:00 p.m.
    Not All Language Model Features Are Linear
    Joshua Engels*, MIT
    Wes Gurnee, MIT
    Isaac Liao, MIT
    Eric J Michaud, MIT
    Max Tegmark, MIT
    (1203-68-43413)
  • 4:00 p.m.
    Machine-learning invariants of arithmetic curves
    Yang-Hui He, London Institute for Mathematical Sciences
    Kyu-Hwan Lee*, University of Connecticut
    Thomas Oliver, University of Westminster
    (1203-11-42882)
  • 5:00 p.m.
    ReLU Neural Networks with Linear Layers Learn Single- and Multiple-Index Models
    Suzanna Parkinson*, University of Chicago
    (1203-68-43602)