Parametrized Quantum Circuits and their approximation capacities in the context of quantum machine learning

• URL: http://arxiv.org/abs/2307.14792v2
• Date: Tue, 7 Nov 2023 14:17:27 GMT
• Title: Parametrized Quantum Circuits and their approximation capacities in the context of quantum machine learning
• Authors: Alberto Manzano, David Dechant, Jordi Tura, Vedran Dunjko
• Abstract summary: Parametrized quantum circuits (PQC) are quantum circuits which consist of both fixed and parametrized gates. We show that PQCs can approximate the space of continuous functions, $p$-integrable functions and the $Hk$ Sobolev spaces under specific distances.
• Score: 1.3108652488669736
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Parametrized quantum circuits (PQC) are quantum circuits which consist of both fixed and parametrized gates. In recent approaches to quantum machine learning (QML), PQCs are essentially ubiquitous and play the role analogous to classical neural networks. They are used to learn various types of data, with an underlying expectation that if the PQC is made sufficiently deep, and the data plentiful, the generalization error will vanish, and the model will capture the essential features of the distribution. While there exist results proving the approximability of square-integrable functions by PQCs under the $L^2$ distance, the approximation for other function spaces and under other distances has been less explored. In this work we show that PQCs can approximate the space of continuous functions, $p$-integrable functions and the $H^k$ Sobolev spaces under specific distances. Moreover, we develop generalization bounds that connect different function spaces and distances. These results provide a theoretical basis for different applications of PQCs, for example for solving differential equations. Furthermore, they provide us with new insight on how to design PQCs and loss functions which better suit the specific needs of the users.

Related papers

• 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)
• Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits [16.460585387762478]
  ized quantum circuits (PQCs) have emerged as a promising approach for quantum neural networks. This paper investigates the expressivity of PQCs for approximating general function classes. We establish the first non-asymptotic approximation error bounds for these functions in terms of the number of qubits, quantum circuit depth, and number of trainable parameters.
  arXiv  Detail & Related papers  (2023-10-11T14:29:11Z)
• Potential and limitations of random Fourier features for dequantizing quantum machine learning [0.5277756703318045]
  Quantum machine learning is arguably one of the most explored applications of near-term quantum devices. Much focus has been put on notions of variational quantum machine learning where parameterized quantum circuits (PQCs) are used as learning models. In this work, we establish necessary and sufficient conditions under which RFF does indeed provide an efficient dequantization of variational quantum machine learning for regression.
  arXiv  Detail & Related papers  (2023-09-20T21:23:52Z)
• Classical-to-Quantum Transfer Learning Facilitates Machine Learning with Variational Quantum Circuit [62.55763504085508]
  We prove that a classical-to-quantum transfer learning architecture using a Variational Quantum Circuit (VQC) improves the representation and generalization (estimation error) capabilities of the VQC model. We show that the architecture of classical-to-quantum transfer learning leverages pre-trained classical generative AI models, making it easier to find the optimal parameters for the VQC in the training stage.
  arXiv  Detail & Related papers  (2023-05-18T03:08:18Z)
• Efficient Mean-Field Simulation of Quantum Circuits Inspired by Density Functional Theory [1.3561290928375374]
  Exact simulations of quantum circuits (QCs) are currently limited to $sim$50 qubits. Here we show simulations of QCs with a method inspired by density functional theory (DFT) Our calculations can predict marginal single-qubit probabilities with over 90% accuracy in several classes of QCs with universal gate sets.
  arXiv  Detail & Related papers  (2022-10-29T02:12:15Z)
• Learning capability of parametrized quantum circuits [2.51657752676152]
  Variational quantum algorithms (VQAs) and their applications in the field of quantum machine learning through parametrized quantum circuits (PQCs) are thought to be one major way of leveraging noisy intermediate-scale quantum computing devices. In this paper, we build upon the work by Schuld et al. and compare popular ans"atze for PQCs through the new measure of learning capability. We also examine dissipative quantum neural networks (dQNN) as introduced by Beer et al. and propose a data re-upload structure for dQNNs to increase their learning capability.
  arXiv  Detail & Related papers  (2022-09-21T13:26:20Z)
• Theory of Quantum Generative Learning Models with Maximum Mean Discrepancy [67.02951777522547]
  We study learnability of quantum circuit Born machines (QCBMs) and quantum generative adversarial networks (QGANs) We first analyze the generalization ability of QCBMs and identify their superiorities when the quantum devices can directly access the target distribution. Next, we prove how the generalization error bound of QGANs depends on the employed Ansatz, the number of qudits, and input states.
  arXiv  Detail & Related papers  (2022-05-10T08:05:59Z)
• Oracle separations of hybrid quantum-classical circuits [68.96380145211093]
  Two models of quantum computation: CQ_d and QC_d. CQ_d captures the scenario of a d-depth quantum computer many times; QC_d is more analogous to measurement-based quantum computation. We show that, despite the similarities between CQ_d and QC_d, the two models are intrinsically, i.e. CQ_d $nsubseteq$ QC_d and QC_d $nsubseteq$ CQ_d relative to an oracle.
  arXiv  Detail & Related papers  (2022-01-06T03:10:53Z)
• Dimensional Expressivity Analysis, best-approximation errors, and automated design of parametric quantum circuits [0.13980986259786224]
  The dimensional expressivity analysis discussed in these proceedings is a means of addressing these counteracting effects. Knowing the dimension of the physical state space then allows us to deduce whether or not the PQC can reach all physical states. This implementation has relatively small overhead costs both for the classical and quantum part of the algorithm and could therefore be used in the future for on-the-fly circuit construction.
  arXiv  Detail & Related papers  (2021-11-22T19:30:54Z)
• FLIP: A flexible initializer for arbitrarily-sized parametrized quantum circuits [105.54048699217668]
  We propose a FLexible Initializer for arbitrarily-sized Parametrized quantum circuits. FLIP can be applied to any family of PQCs, and instead of relying on a generic set of initial parameters, it is tailored to learn the structure of successful parameters. We illustrate the advantage of using FLIP in three scenarios: a family of problems with proven barren plateaus, PQC training to solve max-cut problem instances, and PQC training for finding the ground state energies of 1D Fermi-Hubbard models.
  arXiv  Detail & Related papers  (2021-03-15T17:38:33Z)
• Characterizing the loss landscape of variational quantum circuits [77.34726150561087]
  We introduce a way to compute the Hessian of the loss function of VQCs. We show how this information can be interpreted and compared to classical neural networks.
  arXiv  Detail & Related papers  (2020-08-06T17:48:12Z)

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.