Presentation

<
Neural Control Variates With Automatic Integration
SessionMonte Carlo for PDEs
DescriptionWe present a method that uses arbitrary neural network architectures as control variates with automatic differentiation to improve Monte Carlo methods. Our approach creates unbiased, low-variance, and numerically stable Monte Carlo estimators for various problem setups. We demonstrate our method's advantages in solving Laplace and Poisson equations using Walk-on-Sphere.
Authors
Zilu Li
Cornell University
Guandao Yang
Stanford University
Qingqing Zhao
Stanford University
Xi Deng
Cornell University
Leonidas Guibas
Stanford University
Bharath Hariharan
Cornell University
Gordon Wetzstein
Stanford University
Event Type
Technical Paper
TimeMonday, 29 July 202411:25am - 11:35am MDT
LocationMile High 4
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Monday, 29 July 202410:45am - 12:15pm MDTMile High 4
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Animation
Machine Learning
Rendering
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Monday
Next PresentationNext PresentationA Differential Monte Carlo Solver for the Poisson Equation