We argue and demonstrate that projected entangled-pair states (PEPS) outperform matrix product states significantly for the task of generative modeling of datasets with an intrinsic two-dimensional structure such as images. Our approach builds on a recently introduced algorithm for sampling PEPS, which allows for the efficient optimization and sampling of the distributions.
@article{arxiv.2202.08177,
title = {Generative modeling with projected entangled-pair states},
author = {Tom Vieijra and Laurens Vanderstraeten and Frank Verstraete},
journal= {arXiv preprint arXiv:2202.08177},
year = {2022}
}