Post-variational quantum neural networks
Not on the map. Why?
Abstract (arXiv)
Hybrid quantum-classical computing in the noisy intermediate-scale quantum (NISQ) era with variational algorithms can exhibit barren plateau issues, causing difficult convergence of gradient-based optimization techniques. In this paper, we discuss "post-variational strategies", which shift tunable parameters from the quantum computer to the classical computer, opting for ensemble strategies when optimizing quantum models. We discuss various strategies and design principles for constructing individual quantum circuits, where the resulting ensembles can be optimized with convex programming. Further, we discuss architectural designs of post-variational quantum neural networks and analyze the propagation of estimation errors throughout such neural networks. Finally, we show that empirically, post-variational quantum neural networks using our architectural designs can potentially provide better results than variational algorithms and performance comparable to that of two-layer neural networks.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 32 of its 113 references that are in the map. First posted on arXiv 20 Jul 2023.
Builds on
32 of 113 references.
References · 32
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2021Convex optimizationcited by 2,515
- 2020Variational Quantum Algorithmscited by 692
- 2018Supervised learning with quantum enhanced feature spacescited by 665
- 2018Barren plateaus in quantum neural network training landscapescited by 630
- 2020The power of quantum neural networkscited by 379
- 2020Power of data in quantum machine learningcited by 338
- 2020Predicting Many Properties of a Quantum System from Very Few Measurementscited by 233
- 2020Noise-Induced Barren Plateaus in Variational Quantum Algorithmscited by 193
- 2021Connecting ansatz expressibility to gradient magnitudes and barren plateauscited by 180
- 2020Absence of Barren Plateaus in Quantum Convolutional Neural Networkscited by 125
20 more
- 2020Entanglement Induced Barren Plateauscited by 101
- 2021Quantum machine learning beyond kernel methodscited by 92
- 2022Exponential concentration in quantum kernel methodscited by 90
- 2020Layerwise learning for quantum neural networkscited by 88
- 2019Learning to learn with quantum neural networks via classical neural networkscited by 56
- 2021An end-to-end trainable hybrid classical-quantum classifiercited by 51
- 2022Classical surrogates for quantum learning modelscited by 39
- 2017Quantum Neuron: an elementary building block for machine learning on quantum computerscited by 35
- 2022Learning to predict arbitrary quantum processescited by 35
- 2019Input Redundancy for Parameterized Quantum Circuitscited by 33
- 2016Quantum Perceptron Modelscited by 28
- 2022Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machinescited by 28
- 2021Efficient estimation of Pauli observables by derandomizationcited by 20
- 2020VSQL: Variational Shadow Quantum Learning for Classificationcited by 17
- 2014Simulating a perceptron on a quantum computercited by 16
- 2022Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learningcited by 16
- 2018Quantum algorithms for feedforward neural networkscited by 14
- 2021Nonlinear transformation of complex amplitudes via quantum singular value transformationcited by 9
- 2021Noisy intermediate-scale quantum algorithm for semidefinite programmingcited by 5
- 2021A randomized quantum algorithm for statistical phase estimationcited by 4
Built on by
Citing papers per year: 2024: 2; 2025: 1.
3 papers.