Quantum Tensor Networks, Stochastic Processes, and Weighted Automata

Abstract

Modeling joint probability distributions over sequences has been studied from many perspectives. The physics community developed matrix product states, a tensor-train decomposition for probabilistic modeling, motivated by the need to tractably model many-body systems. But similar models have also been studied in the stochastic processes and weighted automata literature, with little work on how these bodies of work relate to each other. We address this gap by showing how stationary or uniform versions of popular quantum tensor network models have equivalent representations in the stochastic processes and weighted automata literature, in the limit of infinitely long sequences. We demonstrate several equivalence results between models used in these three communities: (i) uniform variants of matrix product states, Born machines and locally purified states from the quantum tensor networks literature, (ii) predictive state representations, hidden Markov models, norm-observable operator models and hidden quantum Markov models from the stochastic process literature,and (iii) stochastic weighted automata, probabilistic automata and quadratic automata from the formal languages literature. Such connections may open the door for results and methods developed in one area to be applied in another.

References in corpus (22)

• Area laws for the entanglement entropy - a review
• Tensorizing Neural Networks
• Matrix product operator representations
• Sequential generation of entangled multi-qubit states
• Matrix-product-groundstates for one-dimensional spin-1 quantum antiferromagnets
• Unsupervised Generative Modeling Using Matrix Product States
• Infinite matrix product states, Conformal Field Theory and the Haldane-Shastry model
• Ultimate tensorization: compressing convolutional and FC layers alike
• Purifications of multipartite states: limitations and constructive methods
• Matrix product operators and states: NP-hardness and undecidability
• Quantum POMDPs
• Long-term Forecasting using Higher Order Tensor RNNs
• Quantum measurement occurrence is undecidable
• Matrix Product Operators for Sequence to Sequence Learning
• Hidden Quantum Markov Models and non-adaptive read-out of many-body states
• Supervised Learning for Dynamical System Learning
• Probabilistic Modeling with Matrix Product States
• Irreducible forms of Matrix Product States: Theory and Applications
• Quantum learning of classical stochastic processes: The Completely-Positive Realization Problem
• Algebraic Geometry of Matrix Product States
• Learning and Inference in Hilbert Space with Quantum Graphical Models
• Tensor Networks for Probabilistic Sequence Modeling