Shortcut Matrix Product States and its applications

TL;DR

This paper introduces Shortcut Matrix Product States (SMPS), enhancing traditional MPS by adding long-range interactions to better capture dependencies in complex systems, with efficient training methods and demonstrated advantages in multiple applications.

Contribution

The paper proposes SMPS, a novel extension of MPS with shortcuts to improve long-range dependence modeling, along with efficient training algorithms and application demonstrations.

Findings

SMPS reduces correlation length compared to MPS.

SMPS outperforms vanilla MPS in function fitting and generative modeling.

SMPS effectively computes partition functions in 2D Ising models.

Abstract

Matrix Product States (MPS), also known as Tensor Train (TT) decomposition in mathematics, has been proposed originally for describing an (especially one-dimensional) quantum system, and recently has found applications in various applications such as compressing high-dimensional data, supervised kernel linear classifier, and unsupervised generative modeling. However, when applied to systems which are not defined on one-dimensional lattices, a serious drawback of the MPS is the exponential decay of the correlations, which limits its power in capturing long-range dependences among variables in the system. To alleviate this problem, we propose to introduce long-range interactions, which act as shortcuts, to MPS, resulting in a new model \textit{ Shortcut Matrix Product States} (SMPS). When chosen properly, the shortcuts can decrease significantly the correlation length of the MPS, while preserving the computational efficiency. We develop efficient training methods of SMPS for various tasks, establish some of their mathematical properties, and show how to find a good location to add shortcuts. Finally, using extensive numerical experiments we evaluate its performance in a variety of applications, including function fitting, partition function calculation of $2-$d Ising model, and unsupervised generative modeling of handwritten digits, to illustrate its advantages over vanilla matrix product states.