The Inductive Bias of Quantum Kernels

• URL: http://arxiv.org/abs/2106.03747v1
• Date: Mon, 7 Jun 2021 16:14:32 GMT
• Title: The Inductive Bias of Quantum Kernels
• Authors: Jonas M. K\"ubler, Simon Buchholz, Bernhard Sch\"olkopf
• Abstract summary: We analyze function classes defined via quantum kernels. We show that finding suitable quantum kernels is not easy because the kernel evaluation might require exponentially many measurements.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: It has been hypothesized that quantum computers may lend themselves well to applications in machine learning. In the present work, we analyze function classes defined via quantum kernels. Quantum computers offer the possibility to efficiently compute inner products of exponentially large density operators that are classically hard to compute. However, having an exponentially large feature space renders the problem of generalization hard. Furthermore, being able to evaluate inner products in high dimensional spaces efficiently by itself does not guarantee a quantum advantage, as already classically tractable kernels can correspond to high- or infinite-dimensional reproducing kernel Hilbert spaces (RKHS). We analyze the spectral properties of quantum kernels and find that we can expect an advantage if their RKHS is low dimensional and contains functions that are hard to compute classically. If the target function is known to lie in this class, this implies a quantum advantage, as the quantum computer can encode this inductive bias, whereas there is no classically efficient way to constrain the function class in the same way. However, we show that finding suitable quantum kernels is not easy because the kernel evaluation might require exponentially many measurements. In conclusion, our message is a somewhat sobering one: we conjecture that quantum machine learning models can offer speed-ups only if we manage to encode knowledge about the problem at hand into quantum circuits, while encoding the same bias into a classical model would be hard. These situations may plausibly occur when learning on data generated by a quantum process, however, they appear to be harder to come by for classical datasets.

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)
• Phase-space negativity as a computational resource for quantum kernel methods [2.5499055723658097]
  Quantum kernel methods are a proposal for achieving quantum computational advantage in machine learning. We provide sufficient conditions for the efficient classical estimation of quantum kernel functions for bosonic systems. Our results underpin the role of the negativity in phase-space quasi-probability distributions as an essential resource in quantum machine learning.
  arXiv  Detail & Related papers  (2024-05-20T21:18:53Z)
• Quantum Machine Learning: Quantum Kernel Methods [0.0]
  Kernel methods are a powerful and popular technique in classical Machine Learning. The use of a quantum feature space that can only be calculated efficiently on a quantum computer potentially allows for deriving a quantum advantage. A data dependent projected quantum kernel was shown to provide significant advantage over classical kernels.
  arXiv  Detail & Related papers  (2024-05-02T23:45:29Z)
• A Kerr kernel quantum learning machine [0.0]
  We propose a quantum hardware kernel implementation scheme based on superconducting quantum circuits. The scheme does not use qubits or quantum circuits but rather exploits the analogue features of Kerr modes.
  arXiv  Detail & Related papers  (2024-04-02T09:50:33Z)
• 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)
• Quantum Machine Learning: from physics to software engineering [58.720142291102135]
  We show how classical machine learning approach can help improve the facilities of quantum computers. We discuss how quantum algorithms and quantum computers may be useful for solving classical machine learning tasks.
  arXiv  Detail & Related papers  (2023-01-04T23:37:45Z)
• 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 kernels with squeezed-state encoding for machine learning [0.0]
  We generalize quantum kernel methods by encoding data into continuous-variable quantum states. The kernels can be calculated on a quantum computer and then are combined with classical machine learning.
  arXiv  Detail & Related papers  (2021-08-25T08:24:54Z)
• 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)
• A rigorous and robust quantum speed-up in supervised machine learning [6.402634424631123]
  In this paper, we establish a rigorous quantum speed-up for supervised classification using a general-purpose quantum learning algorithm. Our quantum classifier is a conventional support vector machine that uses a fault-tolerant quantum computer to estimate a kernel function.
  arXiv  Detail & Related papers  (2020-10-05T17:22:22Z)
• Efficient simulatability of continuous-variable circuits with large Wigner negativity [62.997667081978825]
  Wigner negativity is known to be a necessary resource for computational advantage in several quantum-computing architectures. We identify vast families of circuits that display large, possibly unbounded, Wigner negativity, and yet are classically efficiently simulatable. We derive our results by establishing a link between the simulatability of high-dimensional discrete-variable quantum circuits and bosonic codes.
  arXiv  Detail & Related papers  (2020-05-25T11:03:42Z)

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.