T3.R1.1
A MULTISCALE GEOMETRIC METHOD FOR CAPTURING RELATIONAL TOPIC ALIGNMENT
Conrad Hougen, University of Michigan, United States; Karl Pazdernik, Pacific Northwest National Laboratory, United States; Alfred Hero, University of Michigan, United States
Session:
T3.R1: A Modern Signal Processing Perspective on Machine Learning Lecture
Track:
Special Sessions
Location:
Isabela I
Presentation Time:
Tue, 16 Dec, 17:40 - 18:00 AST (UTC -4)
Session Co-Chairs:
Juan Cervino, Massachusetts Institute of Technology and Navid Azizan, Massachusetts Institute of Technology
Session T3.R1
T3.R1.1: A MULTISCALE GEOMETRIC METHOD FOR CAPTURING RELATIONAL TOPIC ALIGNMENT
Conrad Hougen, University of Michigan, United States; Karl Pazdernik, Pacific Northwest National Laboratory, United States; Alfred Hero, University of Michigan, United States
T3.R1.2: Bilinear decomposition of mixed integer linear programs for multi-agent motion planning on quantum computers
Leopoldo Agorio, Universidad de la República, Uruguay; Santiago Paternain, Rensselaer Polytechnic Institute, Uruguay; Juan Andrés Bazerque, Universidad de la República, Uruguay
T3.R1.3: Generative Models with Trainable Low-Rank Mixture-of-Gaussians Prior and Sparse Routing
Alireza Sadeghi, Abraham Jaeger Mountain, Georgios Giannakis, University of Minnesota, United States
T3.R1.4: Attention: Self-Expression Is All You Need
Rene Vidal, University of Pennsylvania, United States
T3.R1.5: GradNetOT: Learning Optimal Transport Maps with GradNets
Shreyas Chaudhari, Srinivasa Pranav, José M.F. Moura, Carnegie Mellon University, United States
Contacts