Barren plateaus in quantum neural network training landscapes

@article{McClean2018BarrenPI,
  title={Barren plateaus in quantum neural network training landscapes},
  author={Jarrod R. McClean and Sergio Boixo and Vadim N. Smelyanskiy and Ryan Babbush and Hartmut Neven},
  journal={Nature Communications},
  year={2018},
  volume={9}
}
Many experimental proposals for noisy intermediate scale quantum devices involve training a parameterized quantum circuit with a classical optimization loop. Such hybrid quantum-classical algorithms are popular for applications in quantum simulation, optimization, and machine learning. Due to its simplicity and hardware efficiency, random circuits are often proposed as initial guesses for exploring the space of quantum states. We show that the exponential dimension of Hilbert space and the… Expand
Training of quantum circuits on a hybrid quantum computer
TLDR
This study trains generative modeling circuits on a quantum hybrid computer showing an optimization strategy and a resource trade-off and shows that the convergence of the quantum circuit to the target distribution depends critically on both the quantum hardware and classical optimization strategy. Expand
Universal discriminative quantum neural networks
TLDR
This work trains near-term quantum circuits to classify data represented by non-orthogonal quantum probability distributions using the Adam stochastic optimization algorithm, and provides an example of quantum machine learning for a task that has inherently no classical analogue. Expand
Entanglement devised barren plateau mitigation
Hybrid quantum-classical variational algorithms are one of the most propitious implementations of quantum computing on near-term devices, offering classical machine learning support to quantum scaleExpand
Variational quantum unsampling on a quantum photonic processor
A promising route towards the demonstration of near-term quantum advantage (or supremacy) over classical systems relies on running tailored quantum algorithms on noisy intermediate-scale quantumExpand
Exponentially Many Local Minima in Quantum Neural Networks
TLDR
A quantitative investigation on the landscape of loss functions of QNNs is conducted and a class of simple yet extremely hard QNN instances for training is identified and the optimality of the construction is shown by providing an almost matching upper bound on such dependence. Expand
Quantum supremacy with analog quantum processors for material science and machine learning
Quantum supremacy is the ability of quantum processors to outperform classical computers at certain tasks. In digital random quantum circuit approaches for supremacy, the output distribution producedExpand
Variational quantum state diagonalization
Variational hybrid quantum-classical algorithms are promising candidates for near-term implementation on quantum computers. In these algorithms, a quantum computer evaluates the cost of a gateExpand
QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits
  • Hanrui Wang, Yongshan Ding, +4 authors Song Han
  • Computer Science, Physics
  • ArXiv
  • 2021
TLDR
This paper proposes and experimentally implements QuantumNAS, a comprehensive framework for noise-adaptive cosearch of the variational circuit and qubit mapping and proposes to decouple the parameter training and circuit search by introducing a novel gate-sharing SuperCircuit. Expand
Layerwise learning for quantum neural networks
TLDR
This work investigates a layerwise learning strategy for parametrized quantum circuits and shows that when considering sampling noise, this strategy can help avoid the problem of barren plateaus of the error surface due to the low depth of circuits, low number of parameters trained in one step, and larger magnitude of gradients compared to training the full circuit. Expand
Absence of Barren Plateaus in Quantum Convolutional Neural Networks
TLDR
This work rigorously analyze the gradient scaling for the parameters in the QCNN architecture and finds that the variance of the gradient vanishes no faster than polynomially, implying that QCNNs do not exhibit barren plateaus. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 61 REFERENCES
Quantum optimization using variational algorithms on near-term quantum devices
TLDR
The quantum volume as a metric to compare the power of near-term quantum devices is discussed and simple error-mitigation schemes are introduced that could improve the accuracy of determining ground-state energies. Expand
Characterizing quantum supremacy in near-term devices
A critical question for quantum computing in the near future is whether quantum devices without error correction can perform a well-defined computational task beyond the capabilities ofExpand
QVECTOR: an algorithm for device-tailored quantum error correction
Current approaches to fault-tolerant quantum computation will not enable useful quantum computation on near-term devices of 50 to 100 qubits. Leading proposals, such as the color code and surfaceExpand
The theory of variational hybrid quantum-classical algorithms
TLDR
This work develops a variational adiabatic ansatz and explores unitary coupled cluster where it is shown how the use of modern derivative free optimization techniques can offer dramatic computational savings of up to three orders of magnitude over previously used optimization techniques. Expand
Practical optimization for hybrid quantum-classical algorithms
A novel class of hybrid quantum-classical algorithms based on the variational approach have recently emerged from separate proposals addressing, for example, quantum chemistry and combinatorialExpand
Classification with Quantum Neural Networks on Near Term Processors
TLDR
A quantum neural network, QNN, that can represent labeled data, classical or quantum, and be trained by supervised learning, is introduced and it is shown through classical simulation that parameters can be found that allow the QNN to learn to correctly distinguish the two data sets. Expand
The theory of variational hybrid quantum-classical algorithms
Many quantumalgorithms have daunting resource requirements when compared towhat is available today. To address this discrepancy, a quantum-classical hybrid optimization scheme known as ‘theExpand
Quantum Algorithms for Fixed Qubit Architectures
Gate model quantum computers with too many qubits to be simulated by available classical computers are about to arrive. We present a strategy for programming these devices without error correction orExpand
Progress towards practical quantum variational algorithms
The preparation of quantum states using short quantum circuits is one of the most promising near-term applications of small quantum computers, especially if the circuit is short enough and theExpand
Unsupervised Machine Learning on a Hybrid Quantum Computer
Machine learning techniques have led to broad adoption of a statistical model of computing. The statistical distributions natively available on quantum processors are a superset of those availableExpand
...
1
2
3
4
5
...