Expressiveness and Learning of Hidden Quantum Markov Models

Abstract

Extending classical probabilistic reasoning using the quantum mechanical view of probability has been of recent interest, particularly in the development of hidden quantum Markov models (HQMMs) to model stochastic processes. However, there has been little progress in characterizing the expressiveness of such models and learning them from data. We tackle these problems by showing that HQMMs are a special subclass of the general class of observable operator models (OOMs) that do not suffer from the \emph{negative probability problem} by design. We also provide a feasible retraction-based learning algorithm for HQMMs using constrained gradient descent on the Stiefel manifold of model parameters. We demonstrate that this approach is faster and scales to larger models than previous learning algorithms.

arXiv commentarXiv admin note: text overlap with arXiv:1903.03730

References in corpus (4)

• Towards a Formulation of Quantum Theory as a Causally Neutral Theory of Bayesian Inference
• Singular value decomposition and matrix reorderings in quantum information theory
• A Bayesian Probability Calculus for Density Matrices
• Learning Quantum Graphical Models using Constrained Gradient Descent on the Stiefel Manifold