distributed message passing for large scale graphical models n.
Download
Skip this Video
Loading SlideShow in 5 Seconds..
Distributed Message Passing for Large Scale Graphical Models PowerPoint Presentation
Download Presentation
Distributed Message Passing for Large Scale Graphical Models

Loading in 2 Seconds...

play fullscreen
1 / 19

Distributed Message Passing for Large Scale Graphical Models - PowerPoint PPT Presentation


  • 143 Views
  • Uploaded on

Distributed Message Passing for Large Scale Graphical Models. Alexander Schwing Tamir Hazan Marc Pollefeys Raquel Urtasun. CVPR2011. Outline. Introduction Related work Message passing algorithm Distributed convex belief propagation Experiment evaluation Conclusion. Introduction.

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'Distributed Message Passing for Large Scale Graphical Models' - shasta


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
distributed message passing for large scale graphical models

Distributed Message Passing for Large Scale Graphical Models

Alexander Schwing

TamirHazan

Marc Pollefeys

Raquel Urtasun

CVPR2011

outline
Outline
  • Introduction
  • Related work
  • Message passing algorithm
  • Distributed convex belief propagation
  • Experiment evaluation
  • Conclusion
introduction
Introduction
  • Vision problems → discrete labeling problems in an undirected graphical model (Ex : MRF)
    • Belief propagation (BP)
    • Graph cut
      • Depending on the potentials and structure of the graph
  • The main underlying limitations to real-world problems are memory and computation.
introduction1
Introduction
  • A new algorithm
    • distribute and parallelize the computation and memory requirements
    • conserving the convergence and optimality guarantees
  • Computation can be done in parallel by partitioning the graph and imposing agreement between the beliefs in the boundaries.
    • Graph-based optimization program → local optimization problems (one per machine).
    • Messages between machines : Lagrange multipliers
  • Stereo reconstruction from high-resolution image
  • Handle large problems (more than 200 labels in images larger than 10 MPixel)
related work
Related work
  • Provable convergence while still being computationally tractable.
    • parallelizes convex belief propagation
    • conserves its convergence and optimality guarantees
  • Strandmarkand Kahl[24]
    • splitting the model across multiple machines
  • GraphLab
    • assumes that all the data is stored in shared-memory
related work1
Related work
  • Split the message passing task at hand into several local optimization problems that are solved in parallel.
  • To ensure convergence we force the local tasks to communicate occasionally.
  • At the local level we parallelize the message passing algorithm using a greedy vertex coloring
message passing algorithm
Message passing algorithm
  • The joint distribution factors into a product of non-negative functions
    • defines a hypergraphwhose nodes represent the n random variables and the subsets of variables x correspond to its hyperedges.
  • Hypergraph
    • Bipartite graph : factor graph[11]
      • one set of nodes corresponding to the original nodes of the hypergraph : variable nodes
      • the other set consisting of its hyperedges : factor nodes
  • N(i) : all factor nodes that are neighbors of variable node i
message passing algorithm1
Message passing algorithm
  • Maximum a posteriori (MAP) assignment
  • Reformulate the MAP problem as integer linear program.
distributed convex belief propagation
Distributed convex belief propagation
  • Partition the vertices of the graphical model to disjoint subgraphs
    • each computer solves independently a variational program with respect to its subgraph.
  • The distributed solutions are then integrated through message-passing between the subgraphs
    • preserving the consistency of the graphical model.
  • Properties :
    • If (5) is strictly concave then the algorithm converges for all ε >= 0, and converges to the global optimum when ε > 0.
distributed convex belief propagation3
Distributed convex belief propagation
  • Lagrange multipliers :
    • : the marginalization constraints within each computer
    • : the consistency constraints between the different computers
experiment evaluation
Experiment evaluation
  • Stereo reconstruction
    • nine 2.4 GHz x64 Quad-Core computers with 24 GB memory each, connected via a standard local area network
  • libDAI0.2.7 [17] and GraphLAB[16]
experiment evaluation3
Experiment evaluation
  • relative duality gap
conclusion
Conclusion
  • Large scale graphical models by dividing the computation and memory requirements into multiple machines.
  • Convergence and optimality guarantees are preserved.
  • Main benefit : the use of multiple computers.