← Back to papers
2012 NIPS NeurIPS 2012

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.

🌉 Interdisciplinary Bridge — Machine Learning and Mathematics & Optimization
🧭 Keyword Pioneer — conditional markov chains
🐝 Cross-Pollinator — Artificial Intelligence, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Speech & Audio
📈 Trend Setter — Sequence Modeling
🐣 Hot Topic Early Bird — sequence labeling

Authors

Mathieu Sinn , Bei Chen

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Statistical Learning Machine Learning > Optimization & Theory > Theory Mathematics & Optimization > Mathematics > Probability Machine Learning > Bayesian & Probabilistic > Probabilistic Modeling Machine Learning > Core Methods > Graphical Models Machine Learning > Learning Types > Supervised Learning Mathematics & Optimization > Probability > Stochastic Processes Machine Learning > Learning Types > Sequence Modeling

Keywords

sequence labeling theoretical analysis maximum likelihood markov chain maximum likelihood estimation conditional markov chains linear-chain conditional random fields mixing properties model identifiability feature function conditional random field mixing property
Download PDF

Related papers

Kernel Hyperalignment 2012
Fused sparsity and robust estimation for linear models with unknown variance 2012
Slice sampling normalized kernel-weighted completely random measure mixture models 2012
Scaling MPE Inference for Constrained Continuous Markov Random Fields with Consensus Optimization 2012
Matrix reconstruction with the local max norm 2012