Quantum machine learning beyond kernel methods

10/25/2021
by   Sofiène Jerbi, et al.
0

With noisy intermediate-scale quantum computers showing great promise for near-term applications, a number of machine learning algorithms based on parametrized quantum circuits have been suggested as possible means to achieve learning advantages. Yet, our understanding of how these quantum machine learning models compare, both to existing classical models and to each other, remains limited. A big step in this direction has been made by relating them to so-called kernel methods from classical machine learning. By building on this connection, previous works have shown that a systematic reformulation of many quantum machine learning models as kernel models was guaranteed to improve their training performance. In this work, we first extend the applicability of this result to a more general family of parametrized quantum circuit models called data re-uploading circuits. Secondly, we show, through simple constructions and numerical simulations, that models defined and trained variationally can exhibit a critically better generalization performance than their kernel formulations, which is the true figure of merit of machine learning tasks. Our results constitute another step towards a more comprehensive theory of quantum machine learning models next to kernel formulations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/04/2021

Quantum tangent kernel

Quantum kernel method is one of the key approaches to quantum machine le...
research
06/23/2022

Classical surrogates for quantum learning models

The advent of noisy intermediate-scale quantum computers has put the sea...
research
01/26/2021

Quantum machine learning models are kernel methods

With near-term quantum devices available and the race for fault-tolerant...
research
09/19/2023

Coreset selection can accelerate quantum machine learning models with provable generalization

Quantum neural networks (QNNs) and quantum kernels stand as prominent fi...
research
06/29/2023

MNISQ: A Large-Scale Quantum Circuit Dataset for Machine Learning on/for Quantum Computers in the NISQ era

We introduce the first large-scale dataset, MNISQ, for both the Quantum ...
research
07/11/2019

Machine Learning Kernel Method from a Quantum Generative Model

Recently the use of Noisy Intermediate Scale Quantum (NISQ) devices for ...
research
08/05/2020

QUBO Formulations for Training Machine Learning Models

Training machine learning models on classical computers is usually a tim...

Please sign up or login with your details

Forgot password? Click here to reset