Saved in:
Bibliographic Details
Main Authors: González, Fabio A., Gallego, Alejandro, Toledo-Cortés, Santiago, Vargas-Calderón, Vladimir
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2102.04394
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913334551379968
author González, Fabio A.
Gallego, Alejandro
Toledo-Cortés, Santiago
Vargas-Calderón, Vladimir
author_facet González, Fabio A.
Gallego, Alejandro
Toledo-Cortés, Santiago
Vargas-Calderón, Vladimir
contents A density matrix describes the statistical state of a quantum system. It is a powerful formalism to represent both the quantum and classical uncertainty of quantum systems and to express different statistical operations such as measurement, system combination and expectations as linear algebra operations. This paper explores how density matrices can be used as a building block for machine learning models exploiting their ability to straightforwardly combine linear algebra and probability. One of the main results of the paper is to show that density matrices coupled with random Fourier features could approximate arbitrary probability distributions over $\mathbb{R}^n$. Based on this finding the paper builds different models for density estimation, classification and regression. These models are differentiable, so it is possible to integrate them with other differentiable components, such as deep learning architectures and to learn their parameters using gradient-based optimization. In addition, the paper presents optimization-less training strategies based on estimation and model averaging. The models are evaluated in benchmark tasks and the results are reported and discussed.
format Preprint
id arxiv_https___arxiv_org_abs_2102_04394
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Learning with Density Matrices and Random Features
González, Fabio A.
Gallego, Alejandro
Toledo-Cortés, Santiago
Vargas-Calderón, Vladimir
Machine Learning
Artificial Intelligence
Quantum Physics
A density matrix describes the statistical state of a quantum system. It is a powerful formalism to represent both the quantum and classical uncertainty of quantum systems and to express different statistical operations such as measurement, system combination and expectations as linear algebra operations. This paper explores how density matrices can be used as a building block for machine learning models exploiting their ability to straightforwardly combine linear algebra and probability. One of the main results of the paper is to show that density matrices coupled with random Fourier features could approximate arbitrary probability distributions over $\mathbb{R}^n$. Based on this finding the paper builds different models for density estimation, classification and regression. These models are differentiable, so it is possible to integrate them with other differentiable components, such as deep learning architectures and to learn their parameters using gradient-based optimization. In addition, the paper presents optimization-less training strategies based on estimation and model averaging. The models are evaluated in benchmark tasks and the results are reported and discussed.
title Learning with Density Matrices and Random Features
topic Machine Learning
Artificial Intelligence
Quantum Physics
url https://arxiv.org/abs/2102.04394