Next Article in Journal
Multi-Type Node Detection in Network Communities
Previous Article in Journal
A Quantum Cellular Automata Type Architecture with Quantum Teleportation for Quantum Computing
Open AccessArticle

Probabilistic Modeling with Matrix Product States

by James Stokes 1,* and John Terilla 2
1
Flatiron Institute, New York, NY 10010, USA
2
Tunnel, New York, NY 10001, USA
*
Author to whom correspondence should be addressed.
Entropy 2019, 21(12), 1236; https://doi.org/10.3390/e21121236
Received: 13 November 2019 / Revised: 10 December 2019 / Accepted: 12 December 2019 / Published: 17 December 2019
(This article belongs to the Section Quantum Information)
Inspired by the possibility that generative models based on quantum circuits can provide a useful inductive bias for sequence modeling tasks, we propose an efficient training algorithm for a subset of classically simulable quantum circuit models. The gradient-free algorithm, presented as a sequence of exactly solvable effective models, is a modification of the density matrix renormalization group procedure adapted for learning a probability distribution. The conclusion that circuit-based models offer a useful inductive bias for classical datasets is supported by experimental results on the parity learning problem. View Full-Text
Keywords: machine learning; density matrix renormalization group; quantum information machine learning; density matrix renormalization group; quantum information
Show Figures

Figure 1

MDPI and ACS Style

Stokes, J.; Terilla, J. Probabilistic Modeling with Matrix Product States. Entropy 2019, 21, 1236.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop