Active inference for binary symmetric hidden Markov models

DOI10.1007/S10955-015-1321-YMaRDI QIDQ892411zbMATH OpenOpenAlexFDO

Authors A. E. Allahverdyan, Aram Galstyan

Publication date 19 November 2015

Published in Journal of Statistical Physics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1411.0630

zbMATH Keywords

active inferenceIsing modelmaximum aposteriori estimation

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Lattice systems (Ising, dimer, Potts, etc.) and systems on graphs arising in equilibrium statistical mechanics (82B20)

Abstract: We consider active maximum a posteriori (MAP) inference problem for Hidden Markov Models (HMM), where, given an initial MAP estimate of the hidden sequence, we select to label certain states in the sequence to improve the estimation accuracy of the remaining states. We develop an analytical approach to this problem for the case of binary symmetric HMMs, and obtain a closed form solution that relates the expected error reduction to model parameters under the specified active inference scheme. We then use this solution to determine most optimal active inference scheme in terms of error reduction, and examine the relation of those schemes to heuristic principles of uncertainty reduction and solution unicity.

Recommendations

• On the accuracy of the MAP inference in HMMs
• Active inference and agency: optimal control without cost functions
• Active inference, belief propagation, and the Bethe approximation
• scientific article; zbMATH DE number 218980
• Deep active inference

Cites work

• Active learning
• Hidden Markov processes
• scientific article; zbMATH DE number 3131738 (Why is no real title available?)
• scientific article; zbMATH DE number 484156 (Why is no real title available?)
• scientific article; zbMATH DE number 2033345 (Why is no real title available?)
• Optimal value of information in graphical models
• Singular behaviour of certain infinite products of random 2 × 2 matrices
• Statistical mechanics of low-density parity-check codes
• Statistical physics analysis of maximum a posteriori estimation for multi-channel hidden Markov models
• Statistical Physics and Information Theory
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• The entropy of a binary hidden Markov process
• Zero-temperature error-correcting code for a binary symmetric channel

Cited in

(1)

• Thermal transitions in a one-dimensional, finite-size Ising model

This page was built for publication: Active inference for binary symmetric hidden Markov models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q892411)