QuantumNAT: quantum noise-aware training with noise injection, quantization and normalization

@article{Wang2022QuantumNATQN,
  title={QuantumNAT: quantum noise-aware training with noise injection, quantization and normalization},
  author={Hanrui Wang and Jiaqi Gu and Yongshan Ding and Zi-Chen Li and Fred Chong and David Z. Pan and Song Han},
  journal={Proceedings of the 59th ACM/IEEE Design Automation Conference},
  year={2022}
}
  • Hanrui WangJiaqi Gu Song Han
  • Published 21 October 2021
  • Physics, Computer Science
  • Proceedings of the 59th ACM/IEEE Design Automation Conference
Parameterized Quantum Circuits (PQC) are promising towards quantum advantage on near-term quantum hardware. However, due to the large quantum noises (errors), the performance of PQC models has a severe degradation on real quantum devices. Take Quantum Neural Network (QNN) as an example, the accuracy gap between noise-free simulation and noisy results on IBMQ-Yorktown for MNIST-4 classification is over 60%. Existing noise mitigation methods are general ones without leveraging unique… 

QOC: quantum on-chip training with parameter shift and gradient pruning

QOC, the first experimental demonstration of practical on-chip PQC training with parameter shift is presented and probabilistic gradient pruning is proposed to firstly identify gradients with potentially large errors and then remove them.

QuanGCN: Noise-Adaptive Training for Robust Quantum Graph Convolutional Networks

This work proposes quantum graph convolutional networks (QuanGCN), which learns the local message passing among nodes with the sequence of crossing-gate quantum operations, and applies sparse constraint to sparsify the nodes’ connections and relieve the error rate of quantum gates.

QuEst: Graph Transformer for Quantum Circuit Reliability Estimation

A graph transformer model is proposed to leverage classical ML to predict noise impact on circuit fidelity, Inspired by the natural graph representation of quantum circuits, to leverage agraph transformer model to predict the noisy circuit fidelity.

Graph Transformer for Quantum Circuit Reliability Prediction

A case study of the ML for quantum part in TorchQuantum proposes to leverage classical ML to predict noise impact on circuit fidelity, Inspired by the natural graph representation of quantum circuits, to leverage a graph transformer model to predict the noisy circuit fidelity.

Improving Quantum Classifier Performance in NISQ Computers by Voting Strategy from Ensemble Learning

This study suggests that ensemble quantum classifiers be optimized with plurality voting and shows that the suggested method can outperform state-of-the-art on two- and four-class classi fications by up to 16.0% and 6.1% , respectively.

Hyperparameter Importance of Quantum Neural Networks Across Small Datasets

This work applies the functional ANOVA framework to quantum neural networks to analyze which of the hyperparameters were most influential for their predictive performance, and introduces new methodologies to study quantum machine learning models and provides new insights toward quantum model selection.

RobustAnalog: Fast Variation-Aware Analog Circuit Design Via Multi-task RL

This study presents RobustAnalog, a robust circuit design framework that involves the variation information in the optimization process that can significantly reduce required the optimization time by 14×-30×, and provides a feasible method to handle various real silicon conditions.

Hybrid Gate-Pulse Model for Variational Quantum Algorithms

A hybrid gate-pulse model that can mitigate redundancy when quantum gates are eventually transformed into control signals and applied on quantum devices is presented and a performance boost at most 8% with 60% shorter pulse duration in the problem-agnostic layer is achieved.

The Imitation Game: Leveraging CopyCats for Robust Native Gate Selection in NISQ Programs

Application-specific Native Gate Selection (ANGEL) is proposed, which designs a CopyCat that imitates a given program but has a known solution and employs the CopyCat to test different combinations of native gates and learn the optimal combination, which is then used to nativize the given program.

References

SHOWING 1-10 OF 27 REFERENCES

QOC: quantum on-chip training with parameter shift and gradient pruning

QOC, the first experimental demonstration of practical on-chip PQC training with parameter shift is presented and probabilistic gradient pruning is proposed to firstly identify gradients with potentially large errors and then remove them.

Can Noise on Qubits Be Learned in Quantum Neural Network? A Case Study on QuantumFlow (Invited Paper)

This paper targets quantum neural network (QNN), and proposes to learn the errors in the training phase, so that the identified QNN model can be resilient to noise, and can optimize QNN models for different errors in qubits.

Barren plateaus in quantum neural network training landscapes

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.

Classification with Quantum Neural Networks on Near Term Processors

This work introduces a quantum neural network, QNN, that can represent labeled data, classical or quantum, and be trained by supervised learning, and shows through classical simulation that parameters can be found that allow the QNN to learn to correctly distinguish the two data sets.

Noise tailoring for scalable quantum computation via randomized compiling

This work proposes a method for introducing independent random single-qubit gates into the logical circuit in such a way that the effective logical circuit remains unchanged and proves that this randomization tailors the noise into stochastic Pauli errors, which can dramatically reduce error rates while introducing little or no experimental overhead.

A co-design framework of neural networks and quantum circuits towards quantum advantage

A neural network and quantum circuit co-design framework, namely QuantumFlow, is presented, which represents data as unitary matrices to exploit quantum power by encoding n = 2k inputs into k qubits and representing data as random variables to seamlessly connect layers without measurement.

Exploration of Quantum Neural Architecture by Mixing Quantum Neuron Designs: (Invited Paper)

This paper makes the very first attempt to mix quantum neuron designs to build quantum neural architectures, and demonstrates that the identified quantum neural architecture with mixed quantum neurons can achieve 90.62% of accuracy on the MNIST dataset.

Error Mitigation for Short-Depth Quantum Circuits.

Two schemes are presented that mitigate the effect of errors and decoherence in short-depth quantum circuits by resampling randomized circuits according to a quasiprobability distribution.

Quantum embeddings for machine learning

This work proposes to train the first part of the circuit with the objective of maximally separating data classes in Hilbert space, a strategy it calls quantum metric learning, which provides a powerful analytic framework for quantum machine learning.

Quanvolutional neural networks: powering image recognition with quantum circuits

A new type of transformational layer called a quantum convolution, or quanvolutional layer is introduced, which operates on input data by locally transforming the data using a number of random quantum circuits, in a way that is similar to the transformations performed by random convolutional filter layers.