Corpus ID: 226254554

Absence of Barren Plateaus in Quantum Convolutional Neural Networks

@article{Pesah2020AbsenceOB,
  title={Absence of Barren Plateaus in Quantum Convolutional Neural Networks},
  author={Arthur Pesah and M. Cerezo and Samson Wang and T. Volkoff and A. Sornborger and Patrick J. Coles},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.02966}
}
Quantum neural networks (QNNs) have generated excitement around the possibility of efficiently analyzing quantum data. But this excitement has been tempered by the existence of exponentially vanishing gradients, known as barren plateau landscapes, for many QNN architectures. Recently, Quantum Convolutional Neural Networks (QCNNs) have been proposed, involving a sequence of convolutional and pooling layers that reduce the number of qubits while preserving information about relevant data features… Expand
Toward Trainability of Quantum Neural Networks.
TLDR
It is proved that QNNs with tree tensor architectures have gradients that vanish polynomially with the qubit number, and this result holds irrespective of which encoding methods are employed. Expand
Quantum Generative Training Using R\'enyi Divergences
Quantum neural networks (QNNs) are a framework for creating quantum algorithms that promises to combine the speedups of quantum computation with the widespread successes of machine learning. A majorExpand
Quantum convolutional neural network for classical data classification
With the rapid advance of quantum machine learning, several proposals for the quantumanalogue of convolutional neural network (CNN) have emerged. In this work, we benchmark fully parametrized quantumExpand
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
Equivalence of quantum barren plateaus to cost concentration and narrow gorges
TLDR
This work analytically proves the connection between three different landscape features that have been observed for PQCs: exponentially vanishing gradients, exponential cost concentration about the mean, and the exponential narrowness of minina. Expand
Effect of barren plateaus on gradient-free optimization
TLDR
It is shown that gradient-free optimizers do not solve the barren plateau problem, and the main result proves that cost function differences, which are the basis for making decisions in a gradient- free optimization, are exponentially suppressed in a barren plateau. Expand
RGB Image Classification with Quantum Convolutional Ansaetze
  • Yu Jing, Yang Yang, +4 authors Huan Xu
  • Physics, Computer Science
  • ArXiv
  • 2021
TLDR
This is the first work of a quantum convolutional circuit to deal with RGB images effectively, with a higher test accuracy compared to the purely classical CNNs, and it is demonstrated that a larger size of the quantum circuit ansatz improves predictive performance in multiclass classification tasks, providing useful insights for near term quantum algorithm developments. Expand
Variational Quantum Classifiers Through the Lens of the Hessian
TLDR
This paper calculated the Hessian and visualized the loss landscape of variational quantum classifiers at different points in parameter space, and shows that how the adaptive Hessian learning rate can influence the convergence while training the variational circuits. Expand
Quantum Convolutional Neural Networks for High Energy Physics Data Analysis
TLDR
The proposed architecture demonstrates the quantum advantage of learning faster than the classical convolutional neural networks under a similar number of parameters, in addition to faster convergence, the QCNN achieves greater test accuracy compared to CNNs. Expand
Recent advances for quantum classifiers
Machine learning has achieved dramatic success in a broad spectrum of applications. Its interplay with quantum physics may lead to unprecedented perspectives for both fundamental research andExpand
...
1
2
3
4
...

References

SHOWING 1-10 OF 62 REFERENCES
Trainability of Dissipative Perceptron-Based Quantum Neural Networks
TLDR
This work analyzes the gradient scaling (and hence the trainability) for a recently proposed architecture that is called dissipative QNNs (DQNNs), where the input qubits of each layer are discarded at the layer's output and finds that DQNN's can exhibit barren plateaus. Expand
Barren plateaus in quantum neural network training landscapes
TLDR
It is shown that for a wide class of reasonable parameterized quantum circuits, the probability that the gradient along any reasonable direction is non-zero to some fixed precision is exponentially small as a function of the number of qubits. Expand
Learning to learn with quantum neural networks via classical neural networks
TLDR
This work trains classical recurrent neural networks to assist in the quantum learning process, also know as meta-learning, to rapidly find approximate optima in the parameter landscape for several classes of quantum variational algorithms. 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
Cost-Function-Dependent Barren Plateaus in Shallow Quantum Neural Networks
TLDR
Two results are rigorously proved that establish a connection between locality and trainability in VQAs and illustrate these ideas with large-scale simulations of a particular VQA known as quantum autoencoders. Expand
Continuous-variable quantum neural networks
TLDR
A general method for building neural networks on quantum computers and how a classical network can be embedded into the quantum formalism and propose quantum versions of various specialized model such as convolutional, recurrent, and residual networks are introduced. Expand
Training deep quantum neural networks
TLDR
A noise-robust architecture for a feedforward quantum neural network, with qudits as neurons and arbitrary unitary operations as perceptrons, whose training procedure is efficient in the number of layers. Expand
Quantum convolutional neural networks
TLDR
A quantum circuit-based algorithm inspired by convolutional neural networks is shown to successfully perform quantum phase recognition and devise quantum error correcting codes when applied to arbitrary input quantum states. Expand
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
An initialization strategy for addressing barren plateaus in parametrized quantum circuits
TLDR
This technical note theoretically motivate and empirically validate an initialization strategy which can resolve the barren plateau problem for practical applications and shows empirically that variational quantum eigensolvers and quantum neural networks initialized using this strategy can be trained using a gradient based method. Expand
...
1
2
3
4
5
...