A new class of upper bounds on the log partition function

@article{Wainwright2005ANC,
  title={A new class of upper bounds on the log partition function},
  author={Martin J. Wainwright and Tommi S. Jaakkola and Alan S. Willsky},
  journal={IEEE Transactions on Information Theory},
  year={2005},
  volume={51},
  pages={2313-2335}
}
  • Martin J. Wainwright, Tommi S. Jaakkola, Alan S. Willsky
  • Published 2005
  • Computer Science, Mathematics
  • IEEE Transactions on Information Theory
  • We introduce a new class of upper bounds on the log partition function of a Markov random field (MRF). This quantity plays an important role in various contexts, including approximating marginal distributions, parameter estimation, combinatorial enumeration, statistical decision theory, and large-deviations bounds. Our derivation is based on concepts from convex duality and information geometry: in particular, it exploits mixtures of distributions in the exponential domain, and the Legendre… CONTINUE READING

    Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 411 CITATIONS

    Semidefinite methods for approximate inference on graphs with cycles

    Log-determinant relaxation for approximate inference in discrete Markov random fields

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Entropy bounds for a Markov random subfield

    VIEW 1 EXCERPT
    CITES METHODS

    MAP estimation via agreement on trees: message-passing and linear programming

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND

    Maximizing submodular functions using probabilistic graphical models

    VIEW 1 EXCERPT
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2002
    2020

    CITATION STATISTICS

    • 63 Highly Influenced Citations

    • Averaged 21 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.