Characterizing the loss landscape of variational quantum circuits
Open accessThe DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Abstract
Machine learning techniques enhanced by noisy intermediate-scale quantum (NISQ) devices and especially variational quantum circuits (VQC) have recently attracted much interest and have already been benchmarked for certain problems. Inspired by classical deep learning, VQCs are trained by gradient descent methods which allow for efficient training over big parameter spaces. For NISQ sized circuits, such methods show good convergence. There are however still many open questions related to the convergence of the loss function and to the trainability of these circuits in situations of vanishing gradients. Furthermore, it is not clear how ‘good’ the minima are in terms of generalization and stability against perturbations of the data and there is, therefore, a need for tools to quantitatively study the convergence of the VQCs. In this work, we introduce a way to compute the Hessian of the loss function of VQCs and show how to characterize the loss landscape with it. The eigenvalues of the Hessian give information on the local curvature and we discuss how this information can be interpreted and compared to classical neural networks. We benchmark our results on several examples, starting with a simple analytic toy model to provide some intuition about the behaviour of the Hessian, then going to bigger circuits, and also train VQCs on data. Finally, we show how the Hessian can be used to adjust the learning rate for faster convergence during the training of variational circuits.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“For certain loss functions, the Fisher information matrix coincides with the Hessian of the loss function [33].”
From The power of quantum neural networks (2021) · cites this paper as [33]
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
Neural networks and physical systems with emergent collective computational abilities.
Hopfield, J. J. (1982) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.79.8.2554 · Cited by 19,270
Quantum Computing in the NISQ era and beyond
Preskill, J. (2018) · Quantum · doi:10.22331/q-2018-08-06-79 · Cited by 8,830
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
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
Solving the quantum many-body problem with artificial neural networks
Carleo, G., & Troyer, M. (2017) · Science · doi:10.1126/science.aag2302 · Cited by 2,215
Mitarai, K., Negoro, M., Kitagawa, M., & Fujii, K. (2018) · Physical Review A · doi:10.1103/physreva.98.032309 · Cited by 1,639
Quantum Chemistry in the Age of Quantum Computing
Cao, Y., Romero, J., Olson, J. P., Degroote, M., Johnson, P. D., Kieferová, M., Kivlichan, I. D., Menke, T., Peropadre, B., Sawaya, N. P. D., et al. (2019) · Chemical Reviews · doi:10.1021/acs.chemrev.8b00803 · Cited by 1,560
Understanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514
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
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
Sim, S., Johnson, P. D., & Aspuru‐Guzik, A. (2019) · Advanced Quantum Technologies · doi:10.1002/qute.201900070 · Cited by 972
A high-bias, low-variance introduction to Machine Learning for physicists
Mehta, P., Bukov, M., Wang, C.-H., Day, A. G. R., Richardson, C., Fisher, C. K., & Schwab, D. J. (2019) · Physics Reports · doi:10.1016/j.physrep.2019.03.001 · Cited by 920
PennyLane: Automatic differentiation of hybrid quantum-classical computations
Bergholm, V., Izaac, J., Schuld, M., Gogolin, C., Ahmed, S., Ajith, V., Alam, M. S., Alonso-Linaje, G., AkashNarayanan, B., Asadi, A., et al. (2018) · arXiv · doi:10.48550/arxiv.1811.04968 · Cited by 732
Data re-uploading for a universal quantum classifier
Pérez-Salinas, A., Cervera-Lierta, A., Gil-Fuster, E., & Latorre, J. I. (2020) · Quantum · doi:10.22331/q-2020-02-06-226 · Cited by 713
Classification with Quantum Neural Networks on Near Term Processors
Farhi, E., & Neven, H. (2018) · arXiv · doi:10.48550/arxiv.1802.06002 · Cited by 598
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
Keskar, N. S., Mudigere, D., Nocedal, J., Smelyanskiy, M., & Tang, P. T. P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.04836 · Cited by 525
Quantum Generative Adversarial Networks for learning and loading random distributions
Zoufal, C., Lucchi, A., & Woerner, S. (2019) · npj Quantum Information · doi:10.1038/s41534-019-0223-2 · Cited by 480
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
Eigenvalues of the Hessian in Deep Learning: Singularity and BeyondPreprint
Sagun, L., Bottou, L., & LeCun, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.07476 · Cited by 329
An artificial neuron implemented on an actual quantum processor
Tacchino, F., Macchiavello, C., Gerace, D., & Bajoni, D. (2019) · npj Quantum Information · doi:10.1038/s41534-019-0140-4 · Cited by 270
The Break-Even Point on Optimization Trajectories of Deep Neural NetworksPreprint
Jastrzȩbski, S., Szymczak, M., Fort, S., Arpit, D., Tabor, J., Cho, K., & Geras, K. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09572 · Cited by 192
Avoiding local minima in variational quantum eigensolvers with the natural gradient optimizer
Wierichs, D., Gogolin, C., & Kastoryano, M. (2020) · arXiv · doi:10.48550/arxiv.2004.14666 · Cited by 172
Essentially No Barriers in Neural Network Energy Landscape
Draxler, F., Veschgini, K., Manfred Salmhofer, B., & Hamprecht, F. A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.00885 · Cited by 171
Empirical Analysis of the Hessian of Over-Parametrized Neural Networks
Sagun, L., Evci, U., Güney, V. U., Dauphin, Y., & Bottou, L. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.04454 · Cited by 140
Methodology for replacing indirect measurements with direct measurements
Mitarai, K., & Fujii, K. (2019) · Physical Review Research · doi:10.1103/physrevresearch.1.013006 · Cited by 139
Energy landscapes for machine learning
Ballard, A. J., Das, R., Martiniani, S., Mehta, D., Sagun, L., Stevenson, J. D., & Wales, D. J. (2017) · Physical Chemistry Chemical Physics · doi:10.1039/c7cp01108c · Cited by 104
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
Chaudhari, P., Choromanska, A., Soatto, S., LeCun, Y., Baldassi, C., Borgs, C., Chayes, J., Sagun, L., & Zecchina, R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01838 · Cited by 92
Explorations on high dimensional landscapesPreprint
Sagun, L., Güney, V. U., Arous, G. B., & LeCun, Y. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.6615 · Cited by 69
Geometry of learning neural quantum states
Park, C.-Y., & Kastoryano, M. J. (2020) · Physical Review Research · doi:10.1103/physrevresearch.2.023232 · Cited by 64
Negative eigenvalues of the Hessian in deep neural networksPreprint
Alain, G., Roux, N. L., & Manzagol, P.-A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.02366 · Cited by 48
QuCumber: wavefunction reconstruction with neural networks
Beach, M. J. S., Vlugt, I. J. S. D., Golubeva, A., Huembeli, P., Kulchytskyy, B., Luo, X., Melko, R. G., Merali, E., & Torlai, G. (2019) · SciPost Physics · doi:10.21468/scipostphys.7.1.009 · Cited by 45
Self-citationGradient Estimation Schemes for Noisy Functions
Brekelmans, R. C. M., Driessen, L., Hamers, H., et al. (2005) · Journal of Optimization Theory and Applications · doi:10.1007/s10957-005-5496-2 · Cited by 39
On the Benefit of Width for Neural Networks: Disappearance of Bad BasinsPreprint
Li, D., Ding, T., & Sun, R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.11039 · Cited by 28
Mitarai, K., Negoro, M., Kitagawa, M., et al. (2018) · Institutional Repositories DataBase (IRDB) · doi:10.48550/arxiv.1803.00745 · Cited by 9
Trainability of Dissipative Perceptron-Based Quantum Neural Networks
Sharma, K., Cerezo, M., Cincio, L., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.12458
The effect of data encoding on the expressive power of variational quantum machine learning models
Schuld, M., Sweke, R., & Meyer, J. J. (2020) · arXiv · doi:10.48550/arxiv.2008.08605
Higher Order Derivatives of Quantum Neural Networks with Barren Plateaus
Cerezo, M., & Coles, P. J. (2020) · arXiv · doi:10.48550/arxiv.2008.07454
Estimating the gradient and higher-order derivatives on quantum hardware
Mari, A., Bromley, T. R., & Killoran, N. (2020) · arXiv · doi:10.48550/arxiv.2008.06517
Evaluating analytic gradients on quantum hardware
Schuld, M., Bergholm, V., Gogolin, C., Izaac, J., & Killoran, N. (2018) · arXiv · doi:10.48550/arxiv.1811.11184
Chaudhari, A. (2017) · Medicine & Science in Sports & Exercise · doi:10.1249/01.mss.0000517356.60109.86
Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
Cerezo, M., Sone, A., Volkoff, T., Cincio, L., & Coles, P. J. (2020) · arXiv · doi:10.48550/arxiv.2001.00550
A high-bias, low-variance introduction to Machine Learning for physicists
Mehta, P., Bukov, M., Wang, C.-H., Day, A. G. R., Richardson, C., Fisher, C. K., & Schwab, D. J. (2018) · arXiv · doi:10.48550/arxiv.1803.08823
Sim, S., Johnson, P. D., & Aspuru-Guzik, A. (2019) · arXiv · doi:10.48550/arxiv.1905.10876
Phase Detection with Neural Networks: Interpreting the Black Box
Dawid, A., Huembeli, P., Tomza, M., Lewenstein, M., & Dauphin, A. (2020) · arXiv · doi:10.48550/arxiv.2004.04711
Self-citation
Research works printed but not linked: 5
- N. S. Keskar, D. Mudigere, J. Nocedal, M. Smelyanskiy, and P. T. P. Tang, arXiv:1609.04836 [cs, math] (2017), arXiv:1609.04836 [cs, math]. · arXiv
- Le, 2011, ICML
- Y. LeCun, J. S. Denker, and S. A. Solla, in Advances in Neural Information Processing Systems , edited by D. S. Touretzky (1990) pp. 598-605.
- B. Hassibi and D. G. Stork, in Advances in neural information processing systems (1993) p. 164.
- P. Huembeli and A. Dauphin, 'PatrickHuembeli/vqc loss landscapes: ArXiv version v1.1,' https: //github.com/PatrickHuembeli/vqc\_loss\_ landscapes (2020).
Cited by
Variational quantum algorithms
Cerezo, M., Arrasmith, A., Babbush, R., Benjamin, S. C., Endo, S., Fujii, K., McClean, J. R., Mitarai, K., Yuan, X., Cincio, L., et al. (2021) · Nature Reviews Physics · doi:10.1038/s42254-021-00348-9 · Cited by 3,385
“The cost landscapes of VQAs are generally non-convex and can be complicated [83], making it difficult to make general guarantees about the computational expense of the optimizations.”
BackgroundNoisy 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
The 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
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
Exponential concentration in quantum kernel methods
Thanasilp, S., Wang, S., Cerezo, M., & Holmes, Z. (2024) · Nature Communications · doi:10.1038/s41467-024-49287-w · Cited by 189
“This isincontrastto Quantum Neural Networks (QNNs)wherethe loss landscape is generally non-convex 18,19 and can exhibit Barren Pla-teaus (BPs).”
Metadata
- Authors
- Huembeli, P., & Dauphin, A.
- Affiliations
- Institute of Photonic Sciences (ES)
- Corresponding author
- Huembeli, Patrick
- Dauphin, Alexandre
- Venue
- Quantum Science and Technology
- Publisher
- IOP Publishing
- Published
- 2021-02-08
- Volume
- 6
- Issue
- 2
- Pages
- 025011
- ISSN
- 2058-9565 (ISSN-L)
- OpenAlex
- W3047041739
- Cited by
- 71
- References
- 20
- Citations by year
- 2026: 1 · 2025: 9 · 2024: 23 · 2023: 9 · 2022: 13 · 2021: 16
- FWCI
- 5.39
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- publishingsupport.iopscience.iop.org/iop-standard/v1 (vor)
- iopscience.iop.org/info/page/text-and-data-mining (tdm)
- Locations
- Quantum Science and Technology (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- HAL (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Quantum Computing Algorithms and Architecture
- Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Quantum many-body systems
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Keywords
- variational quantum circuits, loss landscape, Hessian eigenvalues, local curvature, trainability, gradient vanishing, adaptive learning rate, NISQ devices, generalization
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.