Gaussian initializations help deep variational quantum circuits escape from the barren plateau

• URL: http://arxiv.org/abs/2203.09376v1
• Date: Thu, 17 Mar 2022 15:06:40 GMT
• Title: Gaussian initializations help deep variational quantum circuits escape from the barren plateau
• Authors: Kaining Zhang and Min-Hsiu Hsieh and Liu Liu and Dacheng Tao
• Abstract summary: Variational quantum circuits have been widely employed in quantum simulation and quantum machine learning in recent years. However, quantum circuits with random structures have poor trainability due to the exponentially vanishing gradient with respect to the circuit depth and the qubit number. This result leads to a general belief that deep quantum circuits will not be feasible for practical tasks.
• Score: 87.04438831673063
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Variational quantum circuits have been widely employed in quantum simulation and quantum machine learning in recent years. However, quantum circuits with random structures have poor trainability due to the exponentially vanishing gradient with respect to the circuit depth and the qubit number. This result leads to a general belief that deep quantum circuits will not be feasible for practical tasks. In this work, we propose an initialization strategy with theoretical guarantees for the vanishing gradient problem in general deep circuits. Specifically, we prove that under proper Gaussian initialized parameters, the norm of the gradient decays at most polynomially when the qubit number and the circuit depth increase. Our theoretical results hold for both the local and the global observable cases, where the latter was believed to have vanishing gradients even for shallow circuits. Experimental results verify our theoretical findings in the quantum simulation and quantum chemistry.

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)
• Improve Variational Quantum Eigensolver by Many-Body Localization [0.18416014644193066]
  Many-body localized floquet system has phase avoiding thermalization. We studied the variance of gradient for parameter updates under this circuit. We designed a new type of variational ansatz, called the'many-body localization ansatz'
  arXiv  Detail & Related papers  (2024-07-16T10:49:40Z)
• Avoiding barren plateaus via Gaussian Mixture Model [6.0599055267355695]
  Variational quantum algorithms are one of the most representative algorithms in quantum computing. They face challenges when dealing with large numbers of qubits, deep circuit layers, or global cost functions, making them often untrainable.
  arXiv  Detail & Related papers  (2024-02-21T03:25:26Z)
• Diamond-shaped quantum circuit for real-time quantum dynamics in one dimension [0.0]
  We show that quantum many-body states can be universally represented using a quantum circuit comprising multi-qubit gates. We also evaluate the efficiency of a quantum circuit constructed with two-qubit gates in quench dynamics for the transverse-field Ising model. Our results reveal that a diamond-shaped quantum circuit, designed to approximate the multi-qubit gate-based quantum circuit, remarkably excels in accurately representing the long-time dynamics of the system.
  arXiv  Detail & Related papers  (2023-11-10T07:07:54Z)
• 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 circuit debugging and sensitivity analysis via local inversions [62.997667081978825]
  We present a technique that pinpoints the sections of a quantum circuit that affect the circuit output the most. We demonstrate the practicality and efficacy of the proposed technique by applying it to example algorithmic circuits implemented on IBM quantum machines.
  arXiv  Detail & Related papers  (2022-04-12T19:39:31Z)
• Toward Trainability of Deep Quantum Neural Networks [87.04438831673063]
  Quantum Neural Networks (QNNs) with random structures have poor trainability due to the exponentially vanishing gradient as the circuit depth and the qubit number increase. We provide the first viable solution to the vanishing gradient problem for deep QNNs with theoretical guarantees.
  arXiv  Detail & Related papers  (2021-12-30T10:27:08Z)
• Schr\"odinger-Heisenberg Variational Quantum Algorithms [1.9887498823918806]
  Recent breakthroughs have opened the possibility to intermediate-scale quantum computing with tens to hundreds of qubits. The extremely high accuracy needed to surpass classical computers poses a critical demand to the circuit depth. Here, we propose a paradigm of Schr"odinger-Heisenberg variational quantum algorithms to resolve this problem.
  arXiv  Detail & Related papers  (2021-12-15T04:53:01Z)
• Capacity and quantum geometry of parametrized quantum circuits [0.0]
  Parametrized quantum circuits can be effectively implemented on current devices. We evaluate the capacity and trainability of these circuits using the geometric structure of the parameter space. Our results enhance the understanding of parametrized quantum circuits for improving variational quantum algorithms.
  arXiv  Detail & Related papers  (2021-02-02T18:16:57Z)
• Boundaries of quantum supremacy via random circuit sampling [69.16452769334367]
  Google's recent quantum supremacy experiment heralded a transition point where quantum computing performed a computational task, random circuit sampling. We examine the constraints of the observed quantum runtime advantage in a larger number of qubits and gates.
  arXiv  Detail & Related papers  (2020-05-05T20:11:53Z)

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.