Power Characterization of Noisy Quantum Kernels
- URL: http://arxiv.org/abs/2401.17526v1
- Date: Wed, 31 Jan 2024 01:02:16 GMT
- Title: Power Characterization of Noisy Quantum Kernels
- Authors: Yabo Wang, Bo Qi, Xin Wang, Tongliang Liu and Daoyi Dong
- Abstract summary: We show that noise may make quantum kernel methods to only have poor prediction capability, even when the generalization error is small.
We provide a crucial warning to employ noisy quantum kernel methods for quantum computation.
- Score: 52.47151453259434
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Quantum kernel methods have been widely recognized as one of promising
quantum machine learning algorithms that have potential to achieve quantum
advantages. In this paper, we theoretically characterize the power of noisy
quantum kernels and demonstrate that under global depolarization noise, for
different input data the predictions of the optimal hypothesis inferred by the
noisy quantum kernel approximately concentrate towards some fixed value. In
particular, we depict the convergence rate in terms of the strength of quantum
noise, the size of training samples, the number of qubits, the number of layers
affected by quantum noises, as well as the number of measurement shots. Our
results show that noises may make quantum kernel methods to only have poor
prediction capability, even when the generalization error is small. Thus, we
provide a crucial warning to employ noisy quantum kernel methods for quantum
computation and the theoretical results can also serve as guidelines when
developing practical quantum kernel algorithms for achieving quantum
advantages.
Related papers
- The curse of random quantum data [62.24825255497622]
We quantify the performances of quantum machine learning in the landscape of quantum data.
We find that the training efficiency and generalization capabilities in quantum machine learning will be exponentially suppressed with the increase in qubits.
Our findings apply to both the quantum kernel method and the large-width limit of quantum neural networks.
arXiv Detail & Related papers (2024-08-19T12:18:07Z) - Understanding and mitigating noise in molecular quantum linear response for spectroscopic properties on quantum computers [0.0]
We present a study of quantum linear response theory obtaining spectroscopic properties on simulated fault-tolerant quantum computers.
This work introduces novel metrics to analyze and predict the origins of noise in the quantum algorithm.
We highlight the significant impact of Pauli saving in reducing measurement costs and noise.
arXiv Detail & Related papers (2024-08-17T23:46:17Z) - In Search of Quantum Advantage: Estimating the Number of Shots in Quantum Kernel Methods [30.565491081930997]
We develop an approach for estimating desired precision of kernel values, which is translated into the number of circuit runs.
We stress that quantum kernel methods should not only be considered from the machine learning performance perspective, but also from the context of the resource consumption.
arXiv Detail & Related papers (2024-07-22T16:29:35Z) - Quantum data learning for quantum simulations in high-energy physics [55.41644538483948]
We explore the applicability of quantum-data learning to practical problems in high-energy physics.
We make use of ansatz based on quantum convolutional neural networks and numerically show that it is capable of recognizing quantum phases of ground states.
The observation of non-trivial learning properties demonstrated in these benchmarks will motivate further exploration of the quantum-data learning architecture in high-energy physics.
arXiv Detail & Related papers (2023-06-29T18:00:01Z) - Practical limitations of quantum data propagation on noisy quantum processors [0.9362259192191963]
We show that owing to the noisy nature of current quantum processors, such a quantum algorithm will require single- and two-qubit gates with very low error probability to produce reliable results.
Specifically, we provide the upper bounds on how the relative error in variational parameters' propagation scales with the probability of noise in quantum hardware.
arXiv Detail & Related papers (2023-06-22T17:12:52Z) - Universal cost bound of quantum error mitigation based on quantum
estimation theory [0.0]
We present a unified approach to analyzing the cost of various quantum error mitigation methods on the basis of quantum estimation theory.
We derive for a generic layered quantum circuit under a wide class of Markovian noise that, unbiased estimation of an observable encounters an exponential growth with the circuit depth in the lower bound on the measurement cost.
Our results contribute to the understanding of the physical limitations of quantum error mitigation and offer a new criterion for evaluating the performance of quantum error mitigation techniques.
arXiv Detail & Related papers (2022-08-19T15:04:36Z) - Noisy Quantum Kernel Machines [58.09028887465797]
An emerging class of quantum learning machines is that based on the paradigm of quantum kernels.
We study how dissipation and decoherence affect their performance.
We show that decoherence and dissipation can be seen as an implicit regularization for the quantum kernel machines.
arXiv Detail & Related papers (2022-04-26T09:52:02Z) - Efficient criteria of quantumness for a large system of qubits [58.720142291102135]
We discuss the dimensionless combinations of basic parameters of large, partially quantum coherent systems.
Based on analytical and numerical calculations, we suggest one such number for a system of qubits undergoing adiabatic evolution.
arXiv Detail & Related papers (2021-08-30T23:50:05Z) - Towards understanding the power of quantum kernels in the NISQ era [79.8341515283403]
We show that the advantage of quantum kernels is vanished for large size datasets, few number of measurements, and large system noise.
Our work provides theoretical guidance of exploring advanced quantum kernels to attain quantum advantages on NISQ devices.
arXiv Detail & Related papers (2021-03-31T02:41:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.