Material Detail

Splash Belief Propagation: Efficient Parallelization Through Asynchronous Scheduling

Splash Belief Propagation: Efficient Parallelization Through Asynchronous Scheduling

This video was recorded at NIPS Workshops, Whistler 2009. In this work we focus on approximate parallel inference in loopy graphical models using loopy belief propagation. We demonstrate that the natural, fully synchronous parallelization of belief propagation is highly inefficient. By bounding the achievable parallel performance of loopy belief propagation on chain graphical models we develop a theoretical understanding of the parallel limitations of belief propagation. We then introduce Splash belief propagation, a parallel asynchronous approach which achieves the optimal bounds and demonstrates linear to super-linear scaling on large graphical models. Finally we discuss how these ideas may be generalized to parallel iterative graph algorithms in the context of our new GraphLab framework.

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Browse...

Disciplines with similar materials as Splash Belief Propagation: Efficient Parallelization Through Asynchronous Scheduling

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.