On the similarity of bandwidth-tuned quantum kernels and classical kernels

• URL: http://arxiv.org/abs/2503.05602v2
• Date: Wed, 16 Apr 2025 08:57:18 GMT
• Title: On the similarity of bandwidth-tuned quantum kernels and classical kernels
• Authors: Roberto Flórez-Ablan, Marco Roth, Jan Schnabel,
• Abstract summary: Quantum kernels (QK) are widely used in quantum machine learning applications.<n>However, their potential to surpass classical machine learning methods on classical datasets remains uncertain.<n>We show that bandwidth tuning results in QKs that closely resemble radial basis function (RBF) kernels.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantum kernels (QK) are widely used in quantum machine learning applications; yet, their potential to surpass classical machine learning methods on classical datasets remains uncertain. This limitation can be attributed to the exponential concentration phenomenon, which can impair both trainability and generalization. A common strategy to alleviate this is bandwidth tuning, which involves rescaling data points in the quantum model to improve generalization. In this work, we numerically demonstrate that optimal bandwidth tuning results in QKs that closely resemble radial basis function (RBF) kernels, leading to a lack of quantum advantage over classical methods. Moreover, we reveal that the size of optimal bandwidth tuning parameters further simplifies QKs, causing them to behave like polynomial kernels, corresponding to a low-order Taylor approximation of a RBF kernel. We thoroughly investigate this for fidelity quantum kernels and projected quantum kernels using various data encoding circuits across several classification datasets. We provide numerical evidence and derive a simple analytical model that elucidates how bandwidth tuning influences key quantities in classification tasks. Overall, our findings shed light on the mechanisms that render QK methods classically simulatable.

Related papers

• Learning out-of-time-ordered correlators with classical kernel methods [3.6538093004443155]
  We investigate whether classical kernel methods can accurately learn the XZ-OTOC and a particular sum of OTOCs. We frame the problem as a regression task, generating small batches of labelled data. We train a variety of standard kernel machines and observe that the Laplacian and radial basis function (RBF) kernels perform best.
  arXiv  Detail & Related papers  (2024-09-03T04:20:24Z)
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [63.733312560668274]
  Given a quantum circuit containing d tunable RZ gates and G-d Clifford gates, can a learner perform purely classical inference to efficiently predict its linear properties? We prove that the sample complexity scaling linearly in d is necessary and sufficient to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d. We devise a kernel-based learning model capable of trading off prediction error and computational complexity, transitioning from exponential to scaling in many practical settings.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• Quantum Kernel Machine Learning With Continuous Variables [0.0]
  We represent quantum kernels as closed form functions for continuous variable quantum computing platforms.<n>We show every kernel can be expressed as the product of a Gaussian and an algebraic function of the parameters of the feature map.<n>We prove kernels defined by feature maps of infinite stellar rank, such as GKP-state encodings, can be approximated arbitrarily well by kernels defined by feature maps of finite stellar rank.
  arXiv  Detail & Related papers  (2024-01-11T03:49:40Z)
• Neural quantum kernels: training quantum kernels with quantum neural networks [0.0]
  We propose using the training of a quantum neural network to construct neural quantum kernels. We present several strategies for constructing neural quantum kernels and propose a scalable method to train an $n$-qubit data re-uploading quantum neural network (QNN)
  arXiv  Detail & Related papers  (2024-01-09T16:08:32Z)
• Quantum-Classical Multiple Kernel Learning [0.0]
  Kernel methods in machine learning is one area where such improvements could be realized in the future. Small and noisy quantum computers can evaluate classically-parametric quantum kernels that capture unique notions of similarity in data. We consider pairwise combinations of classical, quantum-quantum, quantum-classical and QC kernels in the context of multiple kernel (MKL) We show this approach to be effective for enhancing various metrics performance in an MKL setting.
  arXiv  Detail & Related papers  (2023-05-28T12:29:04Z)
• Problem-Dependent Power of Quantum Neural Networks on Multi-Class Classification [83.20479832949069]
  Quantum neural networks (QNNs) have become an important tool for understanding the physical world, but their advantages and limitations are not fully understood. Here we investigate the problem-dependent power of QCs on multi-class classification tasks. Our work sheds light on the problem-dependent power of QNNs and offers a practical tool for evaluating their potential merit.
  arXiv  Detail & Related papers  (2022-12-29T10:46:40Z)
• The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine Learning [52.77024349608834]
  Building a quantum analog of classical deep neural networks represents a fundamental challenge in quantum computing. Key issue is how to address the inherent non-linearity of classical deep learning. We introduce the Quantum Path Kernel, a formulation of quantum machine learning capable of replicating those aspects of deep machine learning.
  arXiv  Detail & Related papers  (2022-12-22T16:06:24Z)
• A didactic approach to quantum machine learning with a single qubit [68.8204255655161]
  We focus on the case of learning with a single qubit, using data re-uploading techniques. We implement the different proposed formulations in toy and real-world datasets using the qiskit quantum computing SDK.
  arXiv  Detail & Related papers  (2022-11-23T18:25:32Z)
• Faster variational quantum algorithms with quantum kernel-based surrogate models [0.0]
  We present a new method for small-to-intermediate scale variational algorithms on noisy quantum processors. Our scheme shifts the computational burden onto the classical component of these hybrid algorithms, greatly reducing the number of queries to the quantum processor.
  arXiv  Detail & Related papers  (2022-11-02T14:11:25Z)
• Automatic and effective discovery of quantum kernels [41.61572387137452]
  Quantum computing can empower machine learning models by enabling kernel machines to leverage quantum kernels for representing similarity measures between data.<n>We present an approach to this problem, which employs optimization techniques, similar to those used in neural architecture search and AutoML.<n>The results obtained by testing our approach on a high-energy physics problem demonstrate that, in the best-case scenario, we can either match or improve testing accuracy with respect to the manual design approach.
  arXiv  Detail & Related papers  (2022-09-22T16:42:14Z)
• 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)
• Quantum Machine Learning with SQUID [64.53556573827525]
  We present the Scaled QUantum IDentifier (SQUID), an open-source framework for exploring hybrid Quantum-Classical algorithms for classification problems. We provide examples of using SQUID in a standard binary classification problem from the popular MNIST dataset.
  arXiv  Detail & Related papers  (2021-04-30T21:34:11Z)

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.