Structural risk minimization for quantum linear classifiers

by   Casper Gyurik, et al.

Quantum machine learning (QML) stands out as one of the typically highlighted candidates for quantum computing's near-term "killer application". In this context, QML models based on parameterized quantum circuits comprise a family of machine learning models that are well suited for implementations on near-term devices and that can potentially harness computational powers beyond what is efficiently achievable on a classical computer. However, how to best use these models – e.g., how to control their expressivity to best balance between training accuracy and generalization performance – is far from understood. In this paper we investigate capacity measures of two closely related QML models called explicit and implicit quantum linear classifiers (also called the quantum variational method and quantum kernel estimator) with the objective of identifying new ways to implement structural risk minimization – i.e., how to balance between training accuracy and generalization performance. In particular, we identify that the rank and Frobenius norm of the observables used in the QML model closely control the model's capacity. Additionally, we theoretically investigate the effect that these model parameters have on the training accuracy of the QML model. Specifically, we show that there exists datasets that require a high-rank observable for correct classification, and that there exists datasets that can only be classified with a given margin using an observable of at least a certain Frobenius norm. Our results provide new options for performing structural risk minimization for QML models.


page 1

page 2

page 3

page 4


Quantum machine learning models are kernel methods

With near-term quantum devices available and the race for fault-tolerant...

Potential and limitations of random Fourier features for dequantizing quantum machine learning

Quantum machine learning is arguably one of the most explored applicatio...

Variational quantum policies for reinforcement learning

Variational quantum circuits have recently gained popularity as quantum ...

Classical surrogates for quantum learning models

The advent of noisy intermediate-scale quantum computers has put the sea...

Ansatz-Independent Variational Quantum Classifier

The paradigm of variational quantum classifiers (VQCs) encodes classical...

Sublinear quantum algorithms for training linear and kernel-based classifiers

We investigate quantum algorithms for classification, a fundamental prob...

Noise reduction using past causal cones in variational quantum algorithms

We introduce an approach to improve the accuracy and reduce the sample c...

Please sign up or login with your details

Forgot password? Click here to reset