Importance of Kernel Bandwidth in Quantum Machine Learning

  title={Importance of Kernel Bandwidth in Quantum Machine Learning},
  author={R.R. Shaydulin and Stefan M. Wild},
Quantum kernel methods are considered a promising avenue for applying quantum computers to machine learning problems. However, recent results overlook the central role hyperparameters play in determining the performance of machine learning methods. In this work we identify the hyperparameter controlling the bandwidth of a quantum kernel and show that it controls the expressivity of the resulting model. We use extensive numerical experiments with multiple quantum kernels and classical datasets… 

Figures from this paper

Bandwidth Enables Generalization in Quantum Kernel Models

Evidence is provided that quantum machine learning methods can generalize well on challenging datasets, including those far outside of the theoretical assumptions.

Exponential concentration and untrainability in quantum kernel methods

This work shows that, under certain conditions, values of quantum kernels over different input data can be exponentially concentrated towards some value, leading to an exponential scaling of the number of measurements required for successful training.

Noisy quantum kernel machines

It is shown that decoherence and dissipation can be seen as an implicit regularization for the quantum kernel machines and an upper bound on the generalization error of the model that involves the average purity of the encoded states is derived.

Quantum kernels to learn the phases of quantum matter

This work uses a support vector machine (with a quantum kernel) to predict and characterize second order quantum phase transitions and presents two algorithms, one based on fidelity and onebased on the fldelity per site, to classify the phases of matter in a quantum processor.

Quantum AI simulator using a hybrid CPU-FPGA approach

This work focuses on quantum kernels empirically designed for image classification and demonstrates a field programmable gate arrays (FPGA) implementation, and shows that the quantum kernel estimation by the heterogeneous CPU–FPGA computing is 470 times faster than that by a conventional CPU implementation.

Provable Advantage in Quantum Phase Learning via Quantum Kernel Alphatron

It is proved that, under widely believed complexity theory assumptions, quantum phase learning problem cannot be efficiently solved by machine learning algorithms using classical resources and classical data, and it is proved the universality of quantum kernel Alphatron in efficiently predicting quantum phases.

Unsupervised quantum machine learning for fraud detection

This work develops quantum protocols for anomaly detection and applies them to the task of credit card fraud detection, and observes that quantum FD can challenge equivalent classical protocols at increasing number of features (equal to the number of qubits for data embedding).

A Survey of Quantum Computing for Finance

A comprehensive summary of the state of the art of quantum computing for financial applications, with particular emphasis on stochastic modeling, optimization, and machine learning, describing how these solutions, adapted to work on a quantum computer, can potentially help to solve financial problems more efficiently and accurately.



The Inductive Bias of Quantum Kernels

It is conjecture that quantum machine learning models can offer speed-ups only if they manage to encode knowledge about the problem at hand into quantum circuits, while encoding the same bias into a classical model would be hard.

Quantum machine learning models are kernel methods

It is shown that most near-term and fault-tolerant quantum models can be replaced by a general support vector machine whose kernel computes distances between data-encoding quantum states, and kernel-based training is guaranteed to find better or equally good quantum models than variational circuit training.

Power of data in quantum machine learning

This work shows that some problems that are classically hard to compute can be easily predicted by classical machines learning from data and proposes a projected quantum model that provides a simple and rigorous quantum speed-up for a learning problem in the fault-tolerant regime.

Quantum Machine Learning using Gaussian Processes with Performant Quantum Kernels

By using approximations of performant classical kernels enhanced with extra quantum resources, this work demonstrates that quantum devices, both in simulation and on hardware, can perform machine learning tasks at least as well as, and many times better than, the classical inspiration.

Quantum Machine Learning in Feature Hilbert Spaces.

This Letter interprets the process of encoding inputs in a quantum state as a nonlinear feature map that maps data to quantum Hilbert space and shows how it opens up a new avenue for the design of quantum machine learning algorithms.

Machine learning of high dimensional data on a noisy quantum processor

A circuit ansatz is constructed that preserves kernel magnitudes that typically otherwise vanish due to an exponentially growing Hilbert space, and error mitigation specific to the task of computing quantum kernels on near-term hardware is implemented.

Quantum embeddings for machine learning

This work proposes to train the first part of the circuit with the objective of maximally separating data classes in Hilbert space, a strategy it calls quantum metric learning, which provides a powerful analytic framework for quantum machine learning.

Supervised learning with quantum-enhanced feature spaces

Two classification algorithms that use the quantum state space to produce feature maps are demonstrated on a superconducting processor, enabling the solution of problems when the feature space is large and the kernel functions are computationally expensive to estimate.

Effect of data encoding on the expressive power of variational quantum-machine-learning models

It is shown that there exist quantum models which can realise all possible sets of Fourier coefficients, and therefore, if the accessible frequency spectrum is asymptotically rich enough, such models are universal function approximators.

A rigorous and robust quantum speed-up in supervised machine learning

A rigorous quantum speed-up for supervised classification using a quantum learning algorithm that only requires classical access to data and achieves high accuracy, robust against additive errors in the kernel entries that arise from finite sampling statistics.