Benign Overfitting with Quantum Kernels

• URL: http://arxiv.org/abs/2503.17020v1
• Date: Fri, 21 Mar 2025 10:30:42 GMT
• Title: Benign Overfitting with Quantum Kernels
• Authors: Joachim Tomasi, Sandrine Anthoine, Hachem Kadri,
• Abstract summary: 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.
• Score: 5.499796332553708
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantum kernels quantify similarity between data points by measuring the inner product between quantum states, computed through quantum circuit measurements. By embedding data into quantum systems, quantum kernel feature maps, that may be classically intractable to compute, could efficiently exploit high-dimensional Hilbert spaces to capture complex patterns. However, designing effective quantum feature maps remains a major challenge. Many quantum kernels, such as the fidelity kernel, suffer from exponential concentration, leading to near-identity kernel matrices that fail to capture meaningful data correlations and lead to overfitting and poor generalization. In this paper, we propose a novel strategy for constructing quantum kernels that achieve good generalization performance, drawing inspiration from benign overfitting in classical machine learning. Our approach introduces the concept of local-global quantum kernels, which combine two complementary components: a local quantum kernel based on measurements of small subsystems and a global quantum kernel derived from full-system measurements. Through numerical experiments, we demonstrate that local-global quantum kernels exhibit benign overfitting, supporting the effectiveness of our approach in enhancing quantum kernel methods.

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)
• 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)
• A Unified Framework for Trace-induced Quantum Kernels [0.0]
  Quantum kernel methods are promising candidates for achieving a practical quantum advantage for certain machine learning tasks. In this work we combine all trace-induced quantum kernels into a common framework. We show numerically that models based on local projected kernels can achieve comparable performance to the global fidelity quantum kernel.
  arXiv  Detail & Related papers  (2023-11-22T17:50:00Z)
• Several fitness functions and entanglement gates in quantum kernel generation [3.6953740776904924]
  Entanglement, a fundamental concept in quantum mechanics, assumes a central role in quantum computing. We investigate the optimal number of entanglement gates in the quantum kernel feature maps by a multi-objective genetic algorithm. Our findings offer valuable guidance for enhancing the efficiency and accuracy of quantum machine learning algorithms.
  arXiv  Detail & Related papers  (2023-08-22T18:35:51Z)
• Numerical evidence against advantage with quantum fidelity kernels on classical data [12.621805903645711]
  We show that quantum kernels suffer from exponential "flattening" of the spectrum as the number of qubits grows. We provide extensive numerical evidence for this phenomenon utilizing multiple previously studied quantum feature maps and both synthetic and real data. Our results show that unless novel techniques are developed to control the inductive bias of quantum kernels, they are unlikely to provide a quantum advantage on classical data.
  arXiv  Detail & Related papers  (2022-11-29T19:23:11Z)
• 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)
• Training Quantum Embedding Kernels on Near-Term Quantum Computers [0.08563354084119063]
  Quantum embedding kernels (QEKs) constructed by embedding data into the Hilbert space of a quantum computer are a particular quantum kernel technique. We first provide an accessible introduction to quantum embedding kernels and then analyze the practical issues arising when realizing them on a noisy near-term quantum computer.
  arXiv  Detail & Related papers  (2021-05-05T18:41:13Z)
• 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)
• The theory of the quantum kernel-based binary classifier [0.8057006406834467]
  kernel method that exploit quantum interference and feature quantum Hilbert space opened up tremendous opportunities for quantum-enhanced machine learning. This work extends the general theory of quantum kernel-based classifiers. Focusing on the squared overlap between quantum states as a similarity measure, the essential and minimal ingredients for the quantum binary classification are examined. The validity of the Hilbert-Schmidt inner product, which becomes the squared overlap for pure states, as a positive definite and symmetric kernel is explicitly shown.
  arXiv  Detail & Related papers  (2020-04-07T15:39:36Z)

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.