PAC-Learning of Markov Models with Hidden State

The standard approach for learning Markov Models with Hidden State uses the Expectation-Maximization framework. While this approach had a significant impact on several practical applications (e.g. speech recognition, biological sequence alignment) it has two major limitations: it requires a known model topology, and learning is only locally optimal. We propose a new PAC framework for learning both the topology and the parameters in partially observable Markov models. Our algorithm learns a Probabilistic Deterministic Finite Automata (PDFA) which approximates a Hidden Markov Model (HMM) up to some desired degree of accuracy. We discuss theoretical conditions under which the algorithm produces an optimal solution (in the PAC-sense) and demonstrate promising performance on simple dynamical systems.

• Type: Conference
• Year: 2006
• Where: ECML
• Authors: Ricard Gavaldà, Philipp W. Keller, Joelle Pineau, Doina Precup
• Keywords: ECML 2006, Hidden Markov Model, Machine Learning, Markov Model, Observable Markov Models