Trainability of Dissipative Perceptron-Based Quantum Neural Networks
Open accessThe DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Abstract
Several architectures have been proposed for quantum neural networks (QNNs), with the goal of efficiently performing machine learning tasks on quantum data. Rigorous scaling results are urgently needed for specific QNN constructions to understand which, if any, will be trainable at a large scale. Here, we analyze the gradient scaling (and hence the trainability) for a recently proposed architecture that we call dissipative QNNs (DQNNs), where the input qubits of each layer are discarded at the layer's output. We find that DQNNs can exhibit barren plateaus, i.e., gradients that vanish exponentially in the number of qubits. Moreover, we provide quantitative bounds on the scaling of the gradient for DQNNs under different conditions, such as different cost functions and circuit depths, and show that trainability is not always guaranteed. Our work represents the first rigorous analysis of the scalability of a perceptron-based QNN.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Quantum Computing in the NISQ era and beyond
Preskill, J. (2018) · Quantum · doi:10.22331/q-2018-08-06-79 · Cited by 8,830
Biamonte, J., Wittek, P., Pancotti, N., Rebentrost, P., Wiebe, N., & Lloyd, S. (2017) · Nature · doi:10.1038/nature23474 · Cited by 4,779
A variational eigenvalue solver on a photonic quantum processor
Peruzzo, A., McClean, J., Shadbolt, P., Yung, M.-H., Zhou, X.-Q., Love, P. J., Aspuru-Guzik, A., & O’Brien, J. L. (2014) · Nature Communications · doi:10.1038/ncomms5213 · Cited by 4,552 · cited 1×
“There, it was shown that variational quantum algorithms [20–30], which aim to train QNNs to accomplish specific tasks, may exhibit gradients that vanish exponentially with the system size.”
BackgroundHardware-efficient variational quantum eigensolver for small molecules and quantum magnets
Kandala, A., Mezzacapo, A., Temme, K., Takita, M., Brink, M., Chow, J. M., & Gambetta, J. M. (2017) · Nature · doi:10.1038/nature23879 · Cited by 2,982 · cited 1×
“For this architecture the ensuing DQNN can be exactly mapped into a layered hardware-efficient ansatz as in [19], where two layers of the DQNN correspond to a single layer of the hardware-efficient ansatz [51].”
MethodSupervised learning with quantum-enhanced feature spaces
Havlíček, V., Córcoles, A. D., Temme, K., Harrow, A. W., Kandala, A., Chow, J. M., & Gambetta, J. M. (2019) · Nature · doi:10.1038/s41586-019-0980-2 · Cited by 2,572
Barren plateaus in quantum neural network training landscapes
McClean, J. R., Boixo, S., Smelyanskiy, V. N., Babbush, R., & Neven, H. (2018) · Nature Communications · doi:10.1038/s41467-018-07090-4 · Cited by 2,329
The theory of variational hybrid quantum-classical algorithms
McClean, J. R., Romero, J., Babbush, R., & Aspuru-Guzik, A. (2016) · New Journal of Physics · doi:10.1088/1367-2630/18/2/023023 · Cited by 2,227
Mitarai, K., Negoro, M., Kitagawa, M., & Fujii, K. (2018) · Physical Review A · doi:10.1103/physreva.98.032309 · Cited by 1,639
Quantum convolutional neural networks
Cong, I., Choi, S., & Lukin, M. D. (2019) · Nature Physics · doi:10.1038/s41567-019-0648-8 · Cited by 1,517
Predicting many properties of a quantum system from very few measurements
Huang, H.-Y., Kueng, R., & Preskill, J. (2020) · Nature Physics · doi:10.1038/s41567-020-0932-7 · Cited by 1,240
The power of quantum neural networks
Abbas, A., Sutter, D., Zoufal, C., Lucchi, A., Figalli, A., & Woerner, S. (2021) · Nature Computational Science · doi:10.1038/s43588-021-00084-1 · Cited by 1,082
Evaluating analytic gradients on quantum hardware
Schuld, M., Bergholm, V., Gogolin, C., Izaac, J., & Killoran, N. (2019) · Physical Review A · doi:10.1103/physreva.99.032331 · Cited by 1,072 · cited 1×
“Such parameterization is widely used as it can allow for a straightforward evaluation of the cost function gradients, and since in general its quantum circuit description can be easily obtained [45–47].”
Cost function dependent barren plateaus in shallow parametrized quantum circuits
Cerezo, M., Sone, A., Volkoff, T., Cincio, L., & Coles, P. J. (2021) · Nature Communications · doi:10.1038/s41467-021-21728-w · Cited by 1,047
Self-citationNoise-induced barren plateaus in variational quantum algorithms
Wang, S., Fontana, E., Cerezo, M., Sharma, K., Sone, A., Cincio, L., & Coles, P. J. (2021) · Nature Communications · doi:10.1038/s41467-021-27045-6 · Cited by 773
Self-citationTraining deep quantum neural networks
Beer, K., Bondarenko, D., Farrelly, T., Osborne, T. J., Salzmann, R., Scheiermann, D., & Wolf, R. (2020) · Nature Communications · doi:10.1038/s41467-020-14454-2 · Cited by 726 · cited 7×
“As shown in [37], the derivative of C ( s ) with respect to s is given by, where now Let us now consider time-step s = 0 .”
BackgroundMethodInfluentialThe quest for a Quantum Neural Network
Schuld, M., Sinayskiy, I., & Petruccione, F. (2014) · Quantum Information Processing · doi:10.1007/s11128-014-0809-8 · Cited by 671 · cited 1×
“Motivated by the success of NNs and the advent of noisy intermediate-scale quantum devices [5], there has been tremendous effort to develop quantum neural networks (QNNs) [6].”
BackgroundClassification with Quantum Neural Networks on Near Term Processors
Farhi, E., & Neven, H. (2018) · arXiv · doi:10.48550/arxiv.1802.06002 · Cited by 598
Quantum autoencoders for efficient compression of quantum data
Romero, J., Olson, J. P., & Aspuru-Guzik, A. (2017) · Quantum Science and Technology · doi:10.1088/2058-9565/aa8072 · Cited by 559 · cited 1×
“Despite several QNN proposals that have been successfully implemented [10–17], more research is needed on the advantages and limitations of specific architectures.”
BackgroundQuantum machine learning: a classical perspective
Ciliberto, C., Herbster, M., Ialongo, A. D., Pontil, M., Rocchetto, A., Severini, S., & Wossnig, L. (2018) · Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rspa.2017.0551 · Cited by 518
Stokes, J., Izaac, J., Killoran, N., & Carleo, G. (2020) · Quantum · doi:10.22331/q-2020-05-25-269 · Cited by 473
Theory of variational quantum simulation
Yuan, X., Endo, S., Zhao, Q., Li, Y., & Benjamin, S. C. (2019) · Quantum · doi:10.22331/q-2019-10-07-191 · Cited by 458
Continuous-variable quantum neural networks
Killoran, N., Bromley, T. R., Arrazola, J. M., Schuld, M., Quesada, N., & Lloyd, S. (2019) · Physical Review Research · doi:10.1103/physrevresearch.1.033063 · Cited by 418
An initialization strategy for addressing barren plateaus in parametrized quantum circuits
Grant, E., Wossnig, L., Ostaszewski, M., & Benedetti, M. (2019) · Quantum · doi:10.22331/q-2019-12-09-214 · Cited by 406
Local Random Quantum Circuits are Approximate Polynomial-Designs
Brandão, F. G. S. L., Harrow, A. W., & Horodecki, M. (2016) · Communications in Mathematical Physics · doi:10.1007/s00220-016-2706-8 · Cited by 404
Quantum-assisted quantum compiling
Khatri, S., LaRose, R., Poremba, A., Cincio, L., Sornborger, A. T., & Coles, P. J. (2019) · Quantum · doi:10.22331/q-2019-05-13-140 · Cited by 382 · cited 1×
“(3) [41, 43].”
Self-citationAbsence of Barren Plateaus in Quantum Convolutional Neural Networks
Pesah, A., Cerezo, M., Wang, S., Volkoff, T., Sornborger, A. T., & Coles, P. J. (2021) · Physical Review X · doi:10.1103/physrevx.11.041011 · Cited by 343
Self-citationAbsence of Barren Plateaus in Quantum Convolutional Neural Networks
Pesah, A., Cerezo, M., Wang, S., Volkoff, T., Sornborger, A. T., & Coles, P. J. (2020) · arXiv · doi:10.48550/arxiv.2011.02966 · Cited by 343
Self-citationExpressive power of parametrized quantum circuits
Du, Y., Hsieh, M.-H., Liu, T., & Tao, D. (2020) · Physical Review Research · doi:10.1103/physrevresearch.2.033125 · Cited by 318
Variational quantum algorithms for discovering Hamiltonian spectra
Jones, T., Endo, S., McArdle, S., Yuan, X., & Benjamin, S. C. (2019) · Physical Review A · doi:10.1103/physreva.99.062304 · Cited by 256
Variational fast forwarding for quantum simulation beyond the coherence time
Cîrstoiu, C., Holmes, Z., Iosue, J., Cincio, L., Coles, P. J., & Sornborger, A. (2020) · npj Quantum Information · doi:10.1038/s41534-020-00302-0 · Cited by 232
Self-citationVariational quantum state diagonalization
LaRose, R., Tikku, A., O’Neel-Judy, É., Cincio, L., & Coles, P. J. (2019) · npj Quantum Information · doi:10.1038/s41534-019-0167-6 · Cited by 199 · cited 1×
“For instance, interesting future research directions are QNN-specific optimizers [54–57], analyzing the resilience of QNNs to noise [22, 41], and strategies to prevent barren plateaus [58–61].”
BackgroundSelf-citationNoise resilience of variational quantum compiling
Sharma, K., Khatri, S., Cerezo, M., & Coles, P. J. (2020) · New Journal of Physics · doi:10.1088/1367-2630/ab784c · Cited by 196 · cited 3×
“If the circuit description of output states is provided, one can employ the inverse of the corresponding unitary on the output of a DQNN [41].”
BackgroundMethodSelf-citationLarge gradients via correlation in random parameterized quantum circuits
Volkoff, T., & Coles, P. J. (2021) · Quantum Science and Technology · doi:10.1088/2058-9565/abd891 · Cited by 143 · cited 1×
“For instance, interesting future research directions are QNN-specific optimizers [54–57], analyzing the resilience of QNNs to noise [22, 41], and strategies to prevent barren plateaus [58–61].”
BackgroundSelf-citationAn Adaptive Optimizer for Measurement-Frugal Variational Algorithms
Kübler, J. M., Arrasmith, A., Cincio, L., & Coles, P. J. (2020) · Quantum · doi:10.22331/q-2020-05-11-263 · Cited by 141
Self-citationUnitary quantum perceptron as efficient universal approximator
Torrontegui, E., & García-Ripoll, J. J. (2019) · EPL (Europhysics Letters) · doi:10.1209/0295-5075/125/30004 · Cited by 102
Altaisky, M. V. (2001) · arXiv · doi:10.48550/arxiv.quant-ph/0107012 · Cited by 101
Practical optimization for hybrid quantum-classical algorithms
Guerreschi, G. G., & Smelyanskiy, M. (2017) · arXiv · doi:10.48550/arxiv.1701.01450 · Cited by 99
Variational consistent histories as a hybrid algorithm for quantum foundations
Arrasmith, A., Cincio, L., Sornborger, A. T., Zurek, W. H., & Coles, P. J. (2019) · Nature Communications · doi:10.1038/s41467-019-11417-0 · Cited by 66
Self-citationEntanglement-Induced Barren Plateaus
Ortiz Marrero, C., Kieferová, M., & Wiebe, N. (2021) · PRX Quantum · doi:10.1103/prxquantum.2.040316 · Cited by 39
Toward Trainability of Quantum Neural Networks
Zhang, K., Hsieh, M.-H., Liu, L., & Tao, D. (2020) · arXiv · doi:10.48550/arxiv.2011.06258 · Cited by 36
Cited by
Noisy intermediate-scale quantum algorithms
Bharti, K., Cervera-Lierta, A., Kyaw, T. H., Haug, T., Alperin-Lea, S., Anand, A., Degroote, M., Heimonen, H., Kottmann, J. S., Menke, T., et al. (2022) · Reviews of Modern Physics · doi:10.1103/revmodphys.94.015004 · Cited by 2,231
Cost function dependent barren plateaus in shallow parametrized quantum circuits
Cerezo, M., Sone, A., Volkoff, T., Cincio, L., & Coles, P. J. (2021) · Nature Communications · doi:10.1038/s41467-021-21728-w · Cited by 1,047
Self-citationThe Variational Quantum Eigensolver: A review of methods and best practices
Tilly, J., Chen, H., Cao, S., Picozzi, D., Setia, K., Li, Y., Grant, E., Wossnig, L., Rungger, I., Booth, G. H., et al. (2022) · Physics Reports · doi:10.1016/j.physrep.2022.08.003 · Cited by 1,031
Noise-induced barren plateaus in variational quantum algorithms
Wang, S., Fontana, E., Cerezo, M., Sharma, K., Sone, A., Cincio, L., & Coles, P. J. (2021) · Nature Communications · doi:10.1038/s41467-021-27045-6 · Cited by 773
Self-citationChallenges and opportunities in quantum machine learning
Cerezo, M., Verdon, G., Huang, H.-Y., Cincio, L., & Coles, P. J. (2022) · Nature Computational Science · doi:10.1038/s43588-022-00311-3 · Cited by 689
Self-citation
Metadata
- Authors
- Sharma, K., Cerezo, M., Cincio, L., & Coles, P. J.
- Venue
- Physical Review Letters
- Publisher
- American Physical Society (APS)
- Published
- 2022-05-06
- Volume
- 128
- Issue
- 18
- Pages
- 180505-180505
- ISSN
- 0031-9007 (ISSN-L)
- 1079-7114
- OpenAlex
- W3030829226
- Cited by
- 159
- References
- 41
- FWCI
- 9.94
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.