The power of quantum neural networks

@article{Abbas2020ThePO,
  title={The power of quantum neural networks},
  author={Amira Abbas and David Sutter and Christa Zoufal and Aur{\'e}lien Lucchi and Alessio Figalli and Stefan Woerner},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.00027}
}
Fault-tolerant quantum computers offer the promise of dramatically improving machine learning through speed-ups in computation or improved model scalability. In the near-term, however, the benefits of quantum machine learning are not so clear. Understanding expressibility and trainability of quantum models-and quantum neural networks in particular-requires further investigation. In this work, we use tools from information geometry to define a notion of expressibility for quantum and classical… 
The dilemma of quantum neural networks
TLDR
Through systematic numerical experiments, it is observed that current quantum neural networks fail to provide any benefit over classical learning models and are forced to rethink the role of current QNNs and to design novel protocols for solving real-world problems with quantum advantages.
Quantum Federated Learning with Quantum Data
TLDR
This paper proposes the first fully quantum federated learning framework that can operate over quantum data and share the learning of quantum circuit parameters in a decentralized manner, and is the first to combine Google’s TensorFlow Federated and Tensor Flow Quantum in a practical implementation.
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.
Quantum machine learning with differential privacy
TLDR
This study develops a hybrid quantum-classical model that is trained to preserve privacy using differentially private optimization algorithm and demonstrates potential to be efficiently implemented on near-term quantum devices (noisy intermediate-scale quantum [NISQ]).
Accelerating variational quantum algorithms with multiple quantum processors
TLDR
An efficient distributed optimization scheme, called QUDIO, that can be readily mixed with other advanced VQAs-based techniques to narrow the gap between the state of the art and applications with quantum advantage.
Single-component gradient rules for variational quantum algorithms
TLDR
This work provides a comprehensive picture of the family of gradient rules that vary parameters of quantum gates individually, and proposes a generalized PSR that expresses all members of the aforementioned family as special cases, and introduces a novel perspective for approaching new gradient rules.
Hybrid Quantum-Classical Graph Convolutional Network
TLDR
This research provides a hybrid quantum-classical graph convolutional network (QGCNN) for learning HEP data that demonstrates an advantage over classical multilayer perceptron and Convolutional neural networks in the aspect of number of parameters.
Federated Quantum Machine Learning
TLDR
The distributed federated learning scheme demonstrated almost the same level of trained model accuracies and yet significantly faster distributed training, and demonstrates a promising future research direction for scaling and privacy aspects.
QNLP in Practice: Running Compositional Models of Meaning on a Quantum Computer
TLDR
Results on the first NLP experiments conducted on Noisy Intermediate-Scale Quantum (NISQ) computers for datasets of size ≥ 100 sentences are presented.
Ju n 20 21 Quantum Natural Gradient for Variational Bayes
TLDR
It is proved that, under standard conditions, the VB algorithm with quantum natural gradient is guaranteed to converge and the classical-quantum-classical handoffs are sufficiently economical to preserve computational efficiency.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 74 REFERENCES
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.
Quantum machine learning: a classical perspective
TLDR
The literature in quantum ML is reviewed and perspectives for a mixed readership of classical ML and quantum computation experts are discussed, with particular emphasis on clarifying the limitations of quantum algorithms, how they compare with their best classical counterparts and why quantum resources are expected to provide advantages for learning problems.
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.
The quest for a Quantum Neural Network
TLDR
This article presents a systematic approach to QNN research, concentrating on Hopfield-type networks and the task of associative memory, and outlines the challenge of combining the nonlinear, dissipative dynamics of neural computing and the linear, unitary dynamics of quantum computing.
Quantum Generative Adversarial Networks for learning and loading random distributions
TLDR
This work uses quantum Generative Adversarial Networks (qGANs) to facilitate efficient learning and loading of generic probability distributions - implicitly given by data samples - into quantum states and can enable the use of potentially advantageous quantum algorithms, such as Quantum Amplitude Estimation.
Supervised learning with quantum-enhanced feature spaces
TLDR
Two classification algorithms that use the quantum state space to produce feature maps are demonstrated on a superconducting processor, enabling the solution of problems when the feature space is large and the kernel functions are computationally expensive to estimate.
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.
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.
Machine learning \& artificial intelligence in the quantum domain
TLDR
The main ideas, recent developments and progress are described in a broad spectrum of research investigating ML and AI in the quantum domain, investigating how results and techniques from one field can be used to solve the problems of the other.
Quantum autoencoders for efficient compression of quantum data
TLDR
The model of a quantum autoencoder is introduced to perform similar tasks on quantum data to compress ground states of the Hubbard model and molecular Hamiltonians and shows an example of a simple programmable circuit that can be trained as an efficient autoenCoder.
...
1
2
3
4
5
...