Saved in:
Bibliographic Details
Main Authors: Guo, Erdong, Draper, David
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2103.08277
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911210066149376
author Guo, Erdong
Draper, David
author_facet Guo, Erdong
Draper, David
contents In this work, we investigate the universal representation capacity of the Matrix Product States (MPS) from the perspective of boolean functions and continuous functions. We show that MPS can accurately realize arbitrary boolean functions by providing a construction method of the corresponding MPS structure for an arbitrarily given boolean gate. Moreover, we prove that the function space of MPS with the scale-invariant sigmoidal activation is dense in the space of continuous functions defined on a compact subspace of the $n$-dimensional real coordinate space $\mathbb{R^{n}}$. We study the relation between MPS and neural networks and show that the MPS with a scale-invariant sigmoidal function is equivalent to a one-hidden-layer neural network equipped with a kernel function. We construct the equivalent neural networks for several specific MPS models and show that non-linear kernels such as the polynomial kernel which introduces the couplings between different components of the input into the model appear naturally in the equivalent neural networks. At last, we discuss the realization of the Gaussian Process (GP) with infinitely wide MPS by studying their equivalent neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2103_08277
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Representation Theorem for Matrix Product States
Guo, Erdong
Draper, David
Machine Learning
Neural and Evolutionary Computing
Quantum Physics
In this work, we investigate the universal representation capacity of the Matrix Product States (MPS) from the perspective of boolean functions and continuous functions. We show that MPS can accurately realize arbitrary boolean functions by providing a construction method of the corresponding MPS structure for an arbitrarily given boolean gate. Moreover, we prove that the function space of MPS with the scale-invariant sigmoidal activation is dense in the space of continuous functions defined on a compact subspace of the $n$-dimensional real coordinate space $\mathbb{R^{n}}$. We study the relation between MPS and neural networks and show that the MPS with a scale-invariant sigmoidal function is equivalent to a one-hidden-layer neural network equipped with a kernel function. We construct the equivalent neural networks for several specific MPS models and show that non-linear kernels such as the polynomial kernel which introduces the couplings between different components of the input into the model appear naturally in the equivalent neural networks. At last, we discuss the realization of the Gaussian Process (GP) with infinitely wide MPS by studying their equivalent neural networks.
title Representation Theorem for Matrix Product States
topic Machine Learning
Neural and Evolutionary Computing
Quantum Physics
url https://arxiv.org/abs/2103.08277