Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization

• URL: http://arxiv.org/abs/2607.01080v1
• Date: Wed, 01 Jul 2026 15:38:00 GMT
• Title: Balancing Expressivity and Learnability in Quantum Kernel Bandit Optimization
• Abstract summary: We develop misspecified GP bandit algorithms and derive regret bounds that characterize the trade-off between approximation error and information gain.<n>Our methods outperform full quantum kernels in sample efficiency, while substantially reducing computational overhead.
• Score: 50.880384999888044
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate Gaussian process (GP) bandit optimization with quantum kernels, assuming the mean reward function lies in the reproducing kernel Hilbert space (RKHS) induced by the quantum kernel. This setting is motivated by NISQ-era tasks such as quantum control, state preparation and variational quantum algorithms. While quantum kernels can offer a `quantum advantage' via domain-specific inductive biases, naïvely using full, high-dimensional kernels increases model complexity and information gain, leading to higher cumulative regret and poor learnability. To address this, we propose projected quantum kernels and classical kernel approximation techniques that reduce feature dimensionality while preserving key quantum properties. Using these approximate kernels, we develop misspecified GP bandit algorithms and derive regret bounds that characterize the trade-off between approximation error and information gain. The regret bounds provide principled guidance for selecting the optimal model complexity. Empirically, our methods outperform full quantum kernels in sample efficiency, while substantially reducing computational overhead, enabling scalable GP optimization for quantum-native applications.

Related papers

• Noise-enhanced quantum kernels on analog quantum computers [5.046032666305414]
  We construct an analog quantum kernel and a hybrid quantum kernel.<n>We show their competitiveness against other kernel methods in a benchmarking task.<n>We also incorporate operational noise into the quantum kernels.
  arXiv  Detail & Related papers  (2026-04-14T09:00:32Z)
• Quantum Generator Kernels [3.609036258672038]
  We propose a generator-based approach to quantum kernels, comprising a set of Variational Generator Groups (VGGs) that merge universal generators into a parameterizable operator.<n>Our empirical results demonstrate superior projection and classification capabilities of the QGK compared to state-of-the-art quantum and classical kernel approaches.
  arXiv  Detail & Related papers  (2026-01-30T22:18:01Z)
• Quantum Circuit-Based Adaptation for Credit Risk Analysis [27.308408027453012]
  Noisy and Intermediate-Scale Quantum, or NISQ, processors are sensitive to noise, prone to quantum decoherence, and are not yet capable of continuous quantum error correction for fault-tolerant quantum computation.<n>We experimentally study how hardware-aware variational quantum circuits on a superconducting quantum processing unit can model distributions relevant to specific use-case applications for Credit Risk Analysis.
  arXiv  Detail & Related papers  (2026-01-11T11:17:37Z)
• VQC-MLPNet: An Unconventional Hybrid Quantum-Classical Architecture for Scalable and Robust Quantum Machine Learning [50.95799256262098]
  Variational quantum circuits (VQCs) hold promise for quantum machine learning but face challenges in expressivity, trainability, and noise resilience.<n>We propose VQC-MLPNet, a hybrid architecture where a VQC generates the first-layer weights of a classical multilayer perceptron during training, while inference is performed entirely classically.
  arXiv  Detail & Related papers  (2025-06-12T01:38:15Z)
• Provably Robust Training of Quantum Circuit Classifiers Against Parameter Noise [49.97673761305336]
  Noise remains a major obstacle to achieving reliable quantum algorithms.<n>We present a provably noise-resilient training theory and algorithm to enhance the robustness of parameterized quantum circuit classifiers.
  arXiv  Detail & Related papers  (2025-05-24T02:51:34Z)
• Benign Overfitting with Quantum Kernels [5.499796332553708]
  Quantum kernels quantify similarity between data points by measuring the inner product between quantum states.<n>We propose a novel strategy for constructing quantum kernels that achieve good generalization performance.
  arXiv  Detail & Related papers  (2025-03-21T10:30:42Z)
• Power Characterization of Noisy Quantum Kernels [52.47151453259434]
  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.
  arXiv  Detail & Related papers  (2024-01-31T01:02:16Z)
• Neural auto-designer for enhanced quantum kernels [59.616404192966016]
  We present a data-driven approach that automates the design of problem-specific quantum feature maps. Our work highlights the substantial role of deep learning in advancing quantum machine learning.
  arXiv  Detail & Related papers  (2024-01-20T03:11:59Z)
• Near-Term Distributed Quantum Computation using Mean-Field Corrections and Auxiliary Qubits [77.04894470683776]
  We propose near-term distributed quantum computing that involve limited information transfer and conservative entanglement production. We build upon these concepts to produce an approximate circuit-cutting technique for the fragmented pre-training of variational quantum algorithms.
  arXiv  Detail & Related papers  (2023-09-11T18:00:00Z)
• 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)

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.