Supervised Learning with Quantum-Inspired Tensor Networks
Machine Learning
2017-05-22 v2 Strongly Correlated Electrons
Machine Learning
Abstract
Tensor networks are efficient representations of high-dimensional tensors which have been very successful for physics and mathematics applications. We demonstrate how algorithms for optimizing such networks can be adapted to supervised learning tasks by using matrix product states (tensor trains) to parameterize models for classifying images. For the MNIST data set we obtain less than 1% test set classification error. We discuss how the tensor network form imparts additional structure to the learned model and suggest a possible generative interpretation.
Cite
@article{arxiv.1605.05775,
title = {Supervised Learning with Quantum-Inspired Tensor Networks},
author = {E. Miles Stoudenmire and David J. Schwab},
journal= {arXiv preprint arXiv:1605.05775},
year = {2017}
}
Comments
11 pages, 15 figures; updated version includes corrections, links to sample codes, expanded discussion, and additional references