Mixing Properties of Conditional Markov Chains with Unbounded Feature Functions
Abstract
Conditional Markov Chains (also known as Linear-Chain Conditional Random Fields in the literature) are a versatile class of discriminative models for the distribution of a sequence of hidden states conditional on a sequence of observable variables. Large-sample properties of Conditional Markov Chains have been first studied by Sinn and Poupart [1]. The paper extends this work in two directions: first, mixing properties of models with unbounded feature functions are being established; second, necessary conditions for model identifiability and the uniqueness of maximum likelihood estimates are being given.
Cite
Text
Sinn and Chen. "Mixing Properties of Conditional Markov Chains with Unbounded Feature Functions." Neural Information Processing Systems, 2012.Markdown
[Sinn and Chen. "Mixing Properties of Conditional Markov Chains with Unbounded Feature Functions." Neural Information Processing Systems, 2012.](https://mlanthology.org/neurips/2012/sinn2012neurips-mixing/)BibTeX
@inproceedings{sinn2012neurips-mixing,
title = {{Mixing Properties of Conditional Markov Chains with Unbounded Feature Functions}},
author = {Sinn, Mathieu and Chen, Bei},
booktitle = {Neural Information Processing Systems},
year = {2012},
pages = {1808-1816},
url = {https://mlanthology.org/neurips/2012/sinn2012neurips-mixing/}
}