Published on Mon Apr 30 2018

Supervised learning with quantum enhanced feature spaces

Vojtech Havlicek, Antonio D. Córcoles, Kristan Temme, Aram W. Harrow, Abhinav Kandala, Jerry M. Chow, Jay M. Gambetta

Machine learning and quantum computing are two technologies each with the potential for altering how computation is performed. Kernel methods for machine learning are ubiquitous for pattern recognition. There are limitations to the successful solution to such problems when the feature space becomes too large.

0
0
0
Abstract

Machine learning and quantum computing are two technologies each with the potential for altering how computation is performed to address previously untenable problems. Kernel methods for machine learning are ubiquitous for pattern recognition, with support vector machines (SVMs) being the most well-known method for classification problems. However, there are limitations to the successful solution to such problems when the feature space becomes large, and the kernel functions become computationally expensive to estimate. A core element to computational speed-ups afforded by quantum algorithms is the exploitation of an exponentially large quantum state space through controllable entanglement and interference. Here, we propose and experimentally implement two novel methods on a superconducting processor. Both methods represent the feature space of a classification problem by a quantum state, taking advantage of the large dimensionality of quantum Hilbert space to obtain an enhanced solution. One method, the quantum variational classifier builds on [1,2] and operates through using a variational quantum circuit to classify a training set in direct analogy to conventional SVMs. In the second, a quantum kernel estimator, we estimate the kernel function and optimize the classifier directly. The two methods present a new class of tools for exploring the applications of noisy intermediate scale quantum computers [3] to machine learning.

Tue Jan 26 2021
Machine Learning
Supervised quantum machine learning models are kernel methods
Researchers became interested in the question of what happens if we replace a supervised machine learning model with a quantum circuit. Such "quantum models" are sometimes called 'quantum neural networks' But their mathematical structure is more closely related to kernel methods.
1
2
14
Mon Oct 05 2020
Machine Learning
A rigorous and robust quantum speed-up in supervised machine learning
Several quantum machine learning algorithms were proposed that promise quantum speed-ups over their classical counterparts. Most of these algorithms either assume quantum access to data or are heuristic in nature with no provable advantage.
4
9
25
Thu Apr 15 2021
Machine Learning
Higgs analysis with quantum classifiers
0
0
0
Tue Sep 10 2019
Machine Learning
Quantum Unsupervised and Supervised Learning on Superconducting Processors
Machine learning algorithms perform well on identifying patterns in many datasets. However, as one increases the size of the data, the time for training and using these statistical models grows quickly. Here, we propose and implement on the IBMQ a quantum analogue to K-means clustering.
0
0
0
Fri Jun 21 2019
Machine Learning
Quantum-Inspired Support Vector Machine
Support vector machine (SVM) is a powerful and flexible supervised learning model. The usual algorithm complexity scales polynomially with the dimension of data space and the number of data points. A quantum SVM algorithm was proposed, which is claimed to achieve an exponential speedup.
0
0
0
Mon Aug 02 2021
Machine Learning
Large-scale quantum machine learning
Quantum computers promise to enhance machine learning for practical applications. Using currently available quantum computers, the MNIST database can be processed within 220 hours instead of 10 years.
7
32
107