Estimation and Marginalization Using the Kikuchi Approximation Methods

DOI10.1162/0899766054026693MaRDI QIDQ5696509zbMATH OpenOpenAlexWikidataFDO

Authors Payam Pakzad, Venkat Anantharam

Publication date 18 October 2005

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/0899766054026693

Mathematics Subject Classification ID

Approximation methods and heuristics in mathematical programming (90C59)

Recommendations

• Convexity arguments for efficient minimization of the Bethe and Kikuchi free energies
• Approximate methods for calculating marginals and likelihoods
• MAP Estimation Via Agreement on Trees: Message-Passing and Linear Programming
• A New Class of Upper Bounds on the Log Partition Function
• Tree-based reparameterization framework for analysis of sum-product and related algorithms

Cites work

• A New Look at the Generalized Distributive Law
• A Theory of Cooperative Phenomena
• A recursive approach to low complexity codes
• CCCP Algorithms to Minimize the Bethe and Kikuchi Free Energies: Convergent Alternatives to Belief Propagation
• Design of capacity-approaching irregular low-density parity-check codes
• On Representatives of Subsets
• The capacity of low-density parity-check codes under message-passing decoding
• The generalized distributive law
• The geometry of turbo-decoding dynamics

Cited in

(4)

• Image labeling based on graphical models using Wasserstein messages and geometric assignment
• Method of Kim-zam: An algorithm for computing the maximum likelihood estimator
• On Kikuchi's path probability method
• Cycle-based cluster variational method for direct and inverse inference

This page was built for publication: Estimation and Marginalization Using the Kikuchi Approximation Methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5696509)