The Complexity of Approximating a Bethe Equilibrium

@article{Shin2014TheCO,
  title={The Complexity of Approximating a Bethe Equilibrium},
  author={Jinwoo Shin},
  journal={IEEE Transactions on Information Theory},
  year={2014},
  volume={60},
  pages={3959-3969}
}
  • Jinwoo Shin
  • Published 2014
  • Computer Science, Mathematics
  • IEEE Transactions on Information Theory
This paper resolves a common complexity issue in the Bethe approximation of statistical physics and the belief propagation (BP) algorithm of artificial intelligence. The Bethe approximation and the BP algorithm are heuristic methods for estimating the partition function and marginal probabilities in graphical models, respectively. The computational complexity of the Bethe approximation is decided by the number of operations required to solve a set of nonlinear equations, the so-called Bethe… Expand
9 Citations
Approximating the Bethe Partition Function
  • 23
  • PDF
Synthesis of MCMC and Belief Propagation
  • 10
  • PDF
MCMC assisted by Belief Propagaion
  • PDF
Inference for Generalized Linear Models via Alternating Directions and Bethe Free Energy Minimization
  • 32
  • PDF
Gauges, Loops, and Polynomials for Partition Functions of Graphical Models
  • 1
  • PDF
Convergence of MCMC and Loopy BP in the Tree Uniqueness Region for the Hard-Core Model
  • 23
  • PDF
Convergence of MCMC and Loopy BP in the Tree Uniqueness Region for the Hard-Core Model
  • 10

References

SHOWING 1-10 OF 34 REFERENCES
Counting Independent Sets Using the Bethe Approximation
  • 31
  • PDF
Constructing free-energy approximations and generalized belief propagation algorithms
  • 1,563
  • PDF
CCCP Algorithms to Minimize the Bethe and Kikuchi Free Energies: Convergent Alternatives to Belief Propagation
  • A. Yuille
  • Mathematics, Computer Science
  • Neural Computation
  • 2002
  • 236
  • PDF
Belief Optimization for Binary Networks: A Stable Alternative to Loopy Belief Propagation
  • 113
  • PDF
Counting without sampling: new algorithms for enumeration problems using statistical physics
  • 52
  • PDF
Loop Series and Bethe Variational Bounds in Attractive Graphical Models
  • 68
  • PDF
The Bethe Partition Function of Log-supermodular Graphical Models
  • N. Ruozzi
  • Computer Science, Mathematics
  • NIPS
  • 2012
  • 60
  • PDF
Loopy Belief Propagation for Approximate Inference: An Empirical Study
  • 1,701
  • PDF
Counting in Graph Covers: A Combinatorial Characterization of the Bethe Entropy Function
  • P. Vontobel
  • Mathematics, Computer Science
  • IEEE Transactions on Information Theory
  • 2013
  • 65
  • PDF
...
1
2
3
4
...