Identifying combinatorially symmetric hidden Markov models

MaRDI QIDQ4685891zbMATH OpenFDO

Authors Daniel Burgarth

Publication date 9 October 2018

Full work available at URL https://arxiv.org/abs/1709.02932

IPFS File on IPFS (Hint: this is only the Hash - if you get a timeout, this file is not available on our server.)

zbMATH Keywords

Markov chainsparameter identificationzero forcing

Mathematics Subject Classification ID

Determinants, permanents, traces, other special matrix functions (15A15) Computational methods in Markov chains (60J22)

Abstract: We provide a sufficient criterion for the unique parameter identification of combinatorially symmetric Hidden Markov Models based on the structure of their transition matrix. If the observed states of the chain form a zero forcing set of the graph of the Markov model then it is uniquely identifiable and an explicit reconstruction method is given.

Recommendations

• Parameter redundancy and identifiability in hidden Markov models
• Identification of hidden Markov models -- uniform LLN-s
• Identifiability of hidden Markov information sources and their minimum degrees of freedom
• Generic identication of binary-valued hidden Markov processes
• Identifiability of parameters in latent structure models with many observed variables

Cites work

• A protocol for cooling and controlling composite systems by local interactions
• Combinatorially symmetric matrices
• Hitting Time and Inverse Problems for Markov Chains
• Inference in hidden Markov models.
• Zero forcing parameters and minimum rank problems

Cited in

(4)

• Can one hear a matrix? Recovering a real symmetric matrix from its spectral data
• Parameter redundancy and identifiability in hidden Markov models
• Generic identication of binary-valued hidden Markov processes
• Identifiability of hidden Markov information sources and their minimum degrees of freedom

This page was built for publication: Identifying combinatorially symmetric hidden Markov models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4685891)