pith. sign in

arxiv: 2511.19289 · v2 · pith:J3PQBABHnew · submitted 2025-11-24 · 🪐 quant-ph · cs.IT· cs.LG· math.IT

Performance Guarantees for Quantum Neural Estimation of Entropies

Sreejith Sreekumar , Ziv Goldfeld , Mark M. Wilde This is my paper

Pith reviewed 2026-05-17 05:58 UTC · model grok-4.3

classification 🪐 quant-ph cs.ITcs.LGmath.IT
keywords quantum neural estimationRényi relative entropycopy complexityThompson metricquantum circuitsperformance boundsentropy estimationsub-Gaussian concentration
0
0 comments X p. Extension
pith:J3PQBABH Add to your LaTeX paper What is a Pith Number? 
\usepackage{pith}
\pithnumber{J3PQBABH}

Prints a linked pith:J3PQBABH badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

The pith

Quantum neural estimators achieve O(d/ε²) copy complexity for measured Rényi relative entropies when density pairs have bounded Thompson metric.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops non-asymptotic performance guarantees for quantum neural estimators that combine classical neural networks with parametrized quantum circuits to estimate measured Rényi relative entropies. It proves error risk bounds together with exponential tail bounds that establish sub-Gaussian concentration of the estimator around the true value. For an appropriate subclass of density operator pairs in dimension d whose Thompson metric is bounded, the required number of copies scales as O(|Θ(U)| d / ε²) with minimax-optimal dependence on the accuracy parameter ε. The same theory yields an improved scaling of O(|Θ(U)| polylog(d) / ε²) when the pairs are additionally permutation invariant. These results supply concrete guidance for choosing sample size, network depth, and circuit parameters in practical deployments.

Core claim

We establish non-asymptotic error risk bounds and exponential tail bounds for quantum neural estimators of measured Rényi relative entropies. For density operator pairs with bounded Thompson metric, the copy complexity is O(|Θ(U)| d / ε²) and exhibits minimax optimal dependence on the accuracy ε. When the pairs are permutation invariant the dimension dependence improves to polylog(d). The analysis applies to a hybrid classical-quantum architecture whose quantum component is a parametrized circuit with parameter set Θ(U).

What carries the argument

Quantum neural estimator formed by a classical neural network coupled to a parametrized quantum circuit with parameter set Θ(U), whose error analysis is controlled by the Thompson metric on the input density operator pair.

If this is right

  • The estimation error concentrates sub-Gaussianly, so that doubling the number of copies halves the typical deviation from the true value.
  • Hyperparameter choices for sample size, network width, and circuit depth can be set directly from the derived bounds rather than by trial and error.
  • The linear dependence on dimension d (or polylog d under permutation invariance) makes the method scalable to moderately large quantum systems.
  • The minimax-optimal scaling in 1/ε² implies that further accuracy improvements cost only quadratically more copies.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same style of analysis may extend to other hybrid quantum-classical estimators used for quantum information quantities beyond Rényi entropies.
  • If physical states encountered in experiments frequently satisfy the bounded-metric condition, the copy-complexity result supplies a practical resource estimate for near-term devices.
  • The improvement under permutation invariance suggests that symmetry-aware circuit designs could further reduce sample requirements in many-body settings.

Load-bearing premise

The density operator pairs must have bounded Thompson metric or be permutation invariant.

What would settle it

An explicit pair of density operators with large Thompson metric for which the number of copies needed to reach additive error ε with a QNE exceeds any constant multiple of |Θ(U)| d / ε², or for which the estimator error fails to exhibit sub-Gaussian tails.

read the original abstract

Estimating quantum entropies and divergences is an important problem in quantum physics, information theory, and machine learning. Quantum neural estimators (QNEs), which utilize a hybrid classical-quantum architecture, have recently emerged as an appealing computational framework for estimating these measures. Such estimators combine classical neural networks with parametrized quantum circuits, and their deployment typically entails tedious tuning of hyperparameters controlling the sample size, network architecture, and circuit topology. This work initiates the study of formal guarantees for QNEs of measured (R\'enyi) relative entropies in the form of non-asymptotic error risk bounds. We further establish exponential tail bounds showing that the error is sub-Gaussian and thus sharply concentrates about the ground truth value. For an appropriate sub-class of density operator pairs on a space of dimension $d$ with bounded Thompson metric, our theory establishes a copy complexity of $O(|\Theta(\mathcal{U})|d/\epsilon^2)$ for QNE with a quantum circuit parameter set $\Theta(\mathcal{U})$, which has minimax optimal dependence on the accuracy $\epsilon$. Additionally, if the density operator pairs are permutation invariant, we improve the dimension dependence above to $O(|\Theta(\mathcal{U})|\mathrm{polylog}(d)/\epsilon^2)$. Our theory aims to facilitate principled implementation of QNEs for measured relative entropies and guide hyperparameter tuning in practice.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper initiates the study of formal non-asymptotic error risk bounds and exponential tail bounds for quantum neural estimators (QNEs) of measured Rényi relative entropies. For density-operator pairs on a d-dimensional space with bounded Thompson metric, it derives a copy complexity of O(|Θ(U)| d / ε²) that is minimax-optimal in ε; the dimension dependence improves to O(|Θ(U)| polylog(d) / ε²) when the pairs are permutation-invariant. The bounds are obtained by applying standard concentration inequalities to a hybrid classical-quantum estimator.

Significance. If the stated bounds hold under the paper's explicit restrictions, the work supplies the first rigorous performance guarantees for QNEs, including optimal dependence on accuracy and explicit tail bounds. This directly addresses the practical need for principled hyperparameter selection in hybrid quantum-classical entropy estimation and supplies a concrete benchmark against which future QNE implementations can be compared.

major comments (2)
  1. [§3] §3 (main theorem on copy complexity): the O(|Θ(U)| d / ε²) bound is derived under the bounded-Thompson-metric restriction; the manuscript should explicitly state whether the same ε-optimal rate can be recovered for a larger class (e.g., via a different covering argument) or whether the restriction is information-theoretically necessary.
  2. [§4] §4 (tail-bound derivation): the sub-Gaussian concentration is obtained from standard inequalities applied to the hybrid estimator; the precise Lipschitz constants or variance proxies that depend on the neural-network and circuit classes Θ(U) are not displayed, making it impossible to verify that the hidden factors remain polynomial in the relevant parameters.
minor comments (2)
  1. [Abstract] The notation |Θ(U)| is introduced without an explicit definition in the abstract or early sections; a one-sentence reminder of its meaning (cardinality of the circuit-parameter set) would improve readability.
  2. [Table 1] Table 1 (or equivalent comparison table) lists prior estimators but omits the precise sample-complexity exponents; adding a column for the ε-dependence would make the optimality claim immediately visible.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their thorough review and positive recommendation for minor revision. We address the major comments below and will incorporate the suggested clarifications in the revised manuscript.

read point-by-point responses

  1. Referee: [§3] §3 (main theorem on copy complexity): the O(|Θ(U)| d / ε²) bound is derived under the bounded-Thompson-metric restriction; the manuscript should explicitly state whether the same ε-optimal rate can be recovered for a larger class (e.g., via a different covering argument) or whether the restriction is information-theoretically necessary.

    Authors: The bounded Thompson metric restriction is crucial in our analysis to bound the sensitivity of the measured Rényi relative entropy with respect to changes in the density operators, which in turn controls the covering numbers of the function class induced by Θ(U). This allows us to achieve the minimax-optimal dependence on ε. We do not currently have a proof that removes this restriction while preserving the rate, nor do we have a matching lower bound showing necessity. In the revised manuscript, we will explicitly discuss this point, stating that extending the result to a larger class remains an open question that may require a different covering argument or alternative techniques. revision: yes

  2. Referee: [§4] §4 (tail-bound derivation): the sub-Gaussian concentration is obtained from standard inequalities applied to the hybrid estimator; the precise Lipschitz constants or variance proxies that depend on the neural-network and circuit classes Θ(U) are not displayed, making it impossible to verify that the hidden factors remain polynomial in the relevant parameters.

    Authors: We agree that displaying the explicit constants would improve verifiability. The sub-Gaussian tail bound follows from applying a concentration inequality (such as McDiarmid's or Bernstein's) to the hybrid classical-quantum estimator. The Lipschitz constant is proportional to the maximum variation of the neural network output over the circuit parameters, which is bounded by a factor depending polynomially on the depth and width of the networks in Θ(U), and similarly for the quantum circuit. In the revised version, we will include the precise expressions for these Lipschitz constants and variance proxies in the main text or an appendix, confirming that all hidden factors are polynomial in the relevant parameters including |Θ(U)|. revision: yes

Circularity Check

0 steps flagged

No significant circularity; minor self-citations not load-bearing

full rationale

The paper derives non-asymptotic error risk bounds and exponential tail bounds for the quantum neural estimator using standard concentration inequalities (e.g., sub-Gaussian tails) applied to the hybrid classical-quantum architecture. The copy-complexity result O(|Θ(U)|d/ε²) is explicitly restricted to the subclass of density-operator pairs with bounded Thompson metric (or the permutation-invariant case) and follows directly from these concentration tools plus the dimension d and parameter count |Θ(U)|; no prediction reduces to a fitted quantity defined inside the paper. External literature is cited for the underlying quantum information measures and concentration results, keeping the central argument independent of any self-citation chain.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The central claim rests on standard concentration-of-measure tools applied to a hybrid estimator whose output is assumed to be Lipschitz with respect to the Thompson metric; no new free parameters are introduced beyond the circuit parameter count |Θ(U)| already present in the estimator definition. The bounded-Thompson-metric condition is treated as a domain restriction rather than an invented entity.

axioms (2)
  • standard math Standard sub-Gaussian concentration inequalities apply to the hybrid classical-quantum estimator output
    Invoked to obtain the exponential tail bounds stated in the abstract
  • domain assumption The estimator is Lipschitz continuous with respect to the Thompson metric on the pair of density operators
    Required for the copy-complexity scaling to hold; appears as the 'appropriate sub-class' qualifier

pith-pipeline@v0.9.0 · 5566 in / 1570 out tokens · 30365 ms · 2026-05-17T05:58:10.676637+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

95 extracted references · 95 canonical work pages · 1 internal anchor

  1. [1]

    Thermodynamik quantenmechanischer gesamtheiten,

    J. von Neumann, “Thermodynamik quantenmechanischer gesamtheiten,”Nachrichten von der Gesellschaft der Wis- senschaften zu G ¨ottingen, Mathematisch-Physikalische Klasse, vol. 1927, pp. 273–291, 1927

    work page 1927

  2. [2]

    A mathematical theory of communication,

    C. E. Shannon, “A mathematical theory of communication,”Bell System Technical Journal, vol. 27, no. 3, pp. 379–423, 1948

    work page 1948

  3. [3]

    On measures of entropy and information,

    A. R ´enyi, “On measures of entropy and information,”Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Contributions to the Theory of Statistics, vol. 4.1, pp. 547–561, Jan. 1961

    work page 1961

  4. [4]

    On information and sufficiency,

    S. Kullback and R. A. Leibler, “On information and sufficiency,”The Annals of Mathematical Statistics, vol. 22, no. 1, pp. 79–86, Mar. 1951

    work page 1951

  5. [5]

    Conditional expectations in an operator algebra IV (entropy and information),

    H. Umegaki, “Conditional expectations in an operator algebra IV (entropy and information),”Kodai Mathematical Seminar Reports, vol. 14, no. 2, pp. 59–85, 1962. 43

    work page 1962

  6. [6]

    Quasi-entropies for states of a von Neumann algebra,

    D. Petz, “Quasi-entropies for states of a von Neumann algebra,”Publications of the Research Institute for Mathematical Sciences, vol. 21, no. 4, pp. 787–800, Aug. 1985

    work page 1985

  7. [7]

    Quasi-entropies for finite quantum systems,

    ——, “Quasi-entropies for finite quantum systems,”Reports on Mathematical Physics, vol. 23, no. 1, pp. 57–65, Feb. 1986

    work page 1986

  8. [8]

    On quantum R ´enyi entropies: A new generalization and some properties,

    M. M ¨uller-Lennert, F. Dupuis, O. Szehr, S. Fehr, and M. Tomamichel, “On quantum R ´enyi entropies: A new generalization and some properties,”Journal of Mathematical Physics, vol. 54, no. 12, p. 122203, 2013

    work page 2013

  9. [9]

    Strong converse for the classical capacity of entanglement-breaking and Hadamard channels via a sandwiched R ´enyi relative entropy,

    M. M. Wilde, A. Winter, and D. Yang, “Strong converse for the classical capacity of entanglement-breaking and Hadamard channels via a sandwiched R ´enyi relative entropy,”Communications in Mathematical Physics, vol. 331, pp. 593–622, 2014

    work page 2014

  10. [10]

    Strong converse and Stein’s lemma in quantum hypothesis testing,

    T. Ogawa and H. Nagaoka, “Strong converse and Stein’s lemma in quantum hypothesis testing,”IEEE Transactions on Information Theory, vol. 46, no. 7, pp. 2428–2433, 2000

    work page 2000

  11. [11]

    On error exponents in quantum hypothesis testing,

    T. Ogawa and M. Hayashi, “On error exponents in quantum hypothesis testing,”IEEE Transactions on Information Theory, vol. 50, no. 6, pp. 1368–1372, 2004

    work page 2004

  12. [12]

    The Chernoff lower bound for symmetric quantum hypothesis testing,

    M. Nussbaum and A. Szkola, “The Chernoff lower bound for symmetric quantum hypothesis testing,”The Annals of Statistics, vol. 37, 08 2006

    work page 2006

  13. [13]

    Asymptotic error rates in quantum hypothesis testing,

    K. Audenaert, M. Nussbaum, A. Szkola, and F. Verstraete, “Asymptotic error rates in quantum hypothesis testing,” Communications in Mathematical Physics, vol. 279, no. 1, pp. 251–283, 2008

    work page 2008

  14. [14]

    On composite quantum hypothesis testing,

    M. Berta, F. Brandao, and C. Hirche, “On composite quantum hypothesis testing,”Communications in Mathematical Physics, vol. 385, 07 2021

    work page 2021

  15. [15]

    Quantum query complexity of entropy estimation,

    T. Li and X. Wu, “Quantum query complexity of entropy estimation,”IEEE Transactions on Information Theory, vol. 65, no. 5, pp. 2899–2921, Mar. 2017

    work page 2017

  16. [16]

    Entanglement spectroscopy with a depth-two quantum circuit,

    Y . Subasi, L. Cincio, and P. J. Coles, “Entanglement spectroscopy with a depth-two quantum circuit,”Journal of Physics A: Mathematical and Theoretical, vol. 52, no. 4, p. 44001, Mar. 2019

    work page 2019

  17. [17]

    Estimating quantum entropy,

    J. Acharya, I. Issa, N. V . Shende, and A. B. Wagner, “Estimating quantum entropy,”IEEE Journal on Selected Areas in Information Theory, vol. 1, no. 2, pp. 454–468, 2020

    work page 2020

  18. [18]

    Quantum algorithm for estimatingα-R ´enyi entropies of quantum states,

    S. Subramanian and M.-H. Hsieh, “Quantum algorithm for estimatingα-R ´enyi entropies of quantum states,”Physical Review A, vol. 104, p. 022428, Aug 2021

    work page 2021

  19. [19]

    Distributional property testing in a quantum world,

    A. Gily ´en and T. Li, “Distributional property testing in a quantum world,” in11th Innovations in Theoretical Computer Science Conference (ITCS 2020), ser. Leibniz International Proceedings in Informatics (LIPIcs), T. Vidick, Ed., vol. 151. Dagstuhl, Germany: Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik, 2020, pp. 25:1–25:19

    work page 2020

  20. [20]

    Sublinear quantum algorithms for estimating von Neumann entropy,

    T. Gur, M.-H. Hsieh, and S. Subramanian, “Sublinear quantum algorithms for estimating von Neumann entropy,” arXiv:2111.11139, Nov. 2021

    work page arXiv 2021

  21. [21]

    Quantum algorithms for estimating quantum entropies,

    Y . Wang, B. Zhao, and X. Wang, “Quantum algorithms for estimating quantum entropies,”Physical Review Applied, vol. 19, no. 4, p. 044041, Apr. 2023

    work page 2023

  22. [22]

    New quantum algorithms for computing quantum entropies and distances,

    Q. Wang, J. Guan, J. Liu, Z. Zhang, and M. Ying, “New quantum algorithms for computing quantum entropies and distances,”IEEE Transactions on Information Theory, vol. 70, no. 8, p. 5653–5680, Aug. 2024

    work page 2024

  23. [23]

    Improved quantum algorithms for fidelity estimation,

    A. Gily ´en and A. Poremba, “Improved quantum algorithms for fidelity estimation,”arXiv:2203.15993, Mar. 2022

    work page arXiv 2022

  24. [24]

    Quantum phase processing and its applications in estimating phase and entropies,

    Y . Wang, L. Zhang, Z. Yu, and X. Wang, “Quantum phase processing and its applications in estimating phase and entropies,” Physical Review A, vol. 108, no. 6, p. 062413, Dec. 2023

    work page 2023

  25. [25]

    Quantum algorithm for fidelity estimation,

    Q. Wang, Z. Zhang, K. Chen, J. Guan, W. Fang, J. Liu, and M. Ying, “Quantum algorithm for fidelity estimation,”IEEE Transactions on Information Theory, vol. 69, no. 1, pp. 273–282, Mar. 2023

    work page 2023

  26. [26]

    A quantum algorithm framework for discrete probability distributions with applications to R´enyi entropy estimation,

    X. Wang, S. Zhang, and T. Li, “A quantum algorithm framework for discrete probability distributions with applications to R´enyi entropy estimation,”IEEE Transactions on Information Theory, vol. 70, no. 5, pp. 3399–3426, 2024

    work page 2024

  27. [27]

    Time-efficient quantum entropy estimator via samplizer,

    Q. Wang and Z. Zhang, “Time-efficient quantum entropy estimator via samplizer,”IEEE Transactions on Information Theory, pp. 1–1, 2025

    work page 2025

  28. [28]

    Lu and K

    Y . Lu and K. Fang, “Estimating quantum relative entropies on quantum computers,”arXiv:2501.07292, 2025. 44

    work page arXiv 2025

  29. [29]

    Quantum neural estimation of entropies,

    Z. Goldfeld, D. Patel, S. Sreekumar, and M. M. Wilde, “Quantum neural estimation of entropies,”Physical Review A, vol. 109, p. 032431, Mar. 2024

    work page 2024

  30. [30]

    Estimating quantum mutual information through a quantum neural network,

    M. Shin, J. Lee, and K. Jeong, “Estimating quantum mutual information through a quantum neural network,”Quantum Information Processing, vol. 23, no. 2, p. 57, 2024

    work page 2024

  31. [31]

    Estimating entanglement entropy via variational quantum circuits with classical neural networks,

    S. Lee, H. Kwon, and J. S. Lee, “Estimating entanglement entropy via variational quantum circuits with classical neural networks,”Physical Review E, vol. 109, p. 044117, Apr. 2024

    work page 2024

  32. [32]

    A variational expression for the relative entropy,

    D. Petz, “A variational expression for the relative entropy,”Communications in Mathematical Physics, vol. 114, no. 2, pp. 345–349, 1988

    work page 1988

  33. [33]

    Springer Science & Business Media, 2007

    ——,Quantum Information Theory and Quantum Statistics. Springer Science & Business Media, 2007

    work page 2007

  34. [34]

    On variational expressions for quantum relative entropies,

    M. Berta, O. Fawzi, and M. Tomamichel, “On variational expressions for quantum relative entropies,”Letters in Mathematical Physics, vol. 107, no. 12, pp. 2239–2265, Dec. 2015

    work page 2015

  35. [35]

    On certain contraction mappings in a partially ordered vector space,

    A. C. Thompson, “On certain contraction mappings in a partially ordered vector space,”Proceedings of the American Mathematical Society, vol. 14, pp. 438–443, 1963

    work page 1963

  36. [36]

    On the relative entropy,

    M. J. Donald, “On the relative entropy,”Communications in Mathematical Physics, vol. 105, no. 1, pp. 13–34, 1986

    work page 1986

  37. [37]

    Relative entropy of entanglement and restricted measurements,

    M. Piani, “Relative entropy of entanglement and restricted measurements,”Physical Review Letters, vol. 103, no. 16, p. 160504, Oct. 2009

    work page 2009

  38. [38]

    The proper formula for relative entropy and its asymptotics in quantum probability,

    F. Hiai and D. Petz, “The proper formula for relative entropy and its asymptotics in quantum probability,”Communications in Mathematical Physics, vol. 143, no. 1, pp. 99 – 114, 1991

    work page 1991

  39. [39]

    Optimal sequence of quantum measurements in the sense of Stein’s lemma in quantum hypothesis testing,

    M. Hayashi, “Optimal sequence of quantum measurements in the sense of Stein’s lemma in quantum hypothesis testing,” Journal of Physics A: Mathematical and General, vol. 35, no. 50, p. 10759, Dec. 2002

    work page 2002

  40. [40]

    Quantum hypothesis testing and the operational interpretation of the quantum R ´enyi relative entropies,

    M. Mosonyi and T. Ogawa, “Quantum hypothesis testing and the operational interpretation of the quantum R ´enyi relative entropies,”Communications in Mathematical Physics, vol. 334, pp. 1617–1648, 2013

    work page 2013

  41. [41]

    Adversarial hypothesis testing and a quantum Stein’s lemma for restricted measurements,

    F. Brand ˜ao, A. W. Harrow, J. R. Lee, and Y . Peres, “Adversarial hypothesis testing and a quantum Stein’s lemma for restricted measurements,”IEEE Transactions on Information Theory, vol. 66, pp. 5037–5054, 2013

    work page 2013

  42. [42]

    Locally-Measured R ´enyi Divergences,

    T. Rippchen, S. Sreekumar, and M. Berta, “Locally-Measured R ´enyi Divergences,”IEEE Transactions on Information Theory, vol. 71, no. 8, pp. 6105–6133, 2025

    work page 2025

  43. [43]

    Distributed quantum hypothesis testing under zero-rate communi- cation constraints,

    S. Sreekumar, C. Hirche, H.-C. Cheng, and M. Berta, “Distributed quantum hypothesis testing under zero-rate communi- cation constraints,”Annales Henri Poincar ´e, 10 2025

    work page 2025

  44. [44]

    Empirical estimation of information measures: A literature guide,

    S. Verd ´u, “Empirical estimation of information measures: A literature guide,”Entropy, vol. 21, no. 8, 2019

    work page 2019

  45. [45]

    Deviation inequalities for R ´enyi divergence estimators via variational expression,

    S. Sreekumar and K. Kato, “Deviation inequalities for R ´enyi divergence estimators via variational expression,” arXiv:2508.09382, 2025

    work page arXiv 2025

  46. [46]

    Sample-optimal tomography of quantum states,

    J. Haah, A. W. Harrow, Z. Ji, X. Wu, and N. Yu, “Sample-optimal tomography of quantum states,” inProceedings of the Forty-Eighth Annual ACM Symposium on Theory of Computing, ser. STOC ’16. New York, NY , USA: Association for Computing Machinery, 2016, p. 913–925

    work page 2016

  47. [47]

    How to learn a quantum state,

    J. Wright, “How to learn a quantum state,” Ph.D. dissertation, Carnegie Mellon University, 2016. [Online]. Available: http://reports-archive.adm.cs.cmu.edu/anon/2016/CMU-CS-16-108.pdf

    work page 2016

  48. [48]

    Efficient quantum tomography,

    R. O’Donnell and J. Wright, “Efficient quantum tomography,” inProceedings of the Forty-Eighth Annual ACM Symposium on Theory of Computing, ser. STOC ’16. New York, NY , USA: Association for Computing Machinery, 2016, p. 899–912

    work page 2016

  49. [49]

    An improved sample complexity lower bound for (fidelity) quantum state tomography,

    H. Yuen, “An improved sample complexity lower bound for (fidelity) quantum state tomography,”Quantum, vol. 7, p. 890, Jan. 2023

    work page 2023

  50. [50]

    Quantum machine learning,

    J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe, and S. Lloyd, “Quantum machine learning,”Nature, vol. 549, no. 7671, pp. 195–202, Sep. 2017

    work page 2017

  51. [51]

    Variational Quantum Fidelity Estimation,

    M. Cerezo, A. Poremba, L. Cincio, and P. J. Coles, “Variational Quantum Fidelity Estimation,”Quantum, vol. 4, p. 248, Mar. 2020. 45

    work page 2020

  52. [52]

    Variational quantum algorithms,

    M. Cerezo, A. Arrasmith, R. Babbush, S. C. Benjamin, S. Endo, K. Fujii, J. R. McClean, K. Mitarai, X. Yuan, L. Cincio, and P. J. Coles, “Variational quantum algorithms,”Nature Reviews Physics, vol. 3, no. 9, pp. 625–644, Aug. 2021

    work page 2021

  53. [53]

    Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machines,

    J. J ¨ager and R. V . Krems, “Universal expressiveness of variational quantum classifiers and quantum kernels for support vector machines,”Nature Communications, vol. 14, no. 1, p. 576, Feb. 2023

    work page 2023

  54. [54]

    Estimating divergence functionals and the likelihood ratio by convex risk minimization,

    X. Nguyen, M. J. Wainwright, and M. I. Jordan, “Estimating divergence functionals and the likelihood ratio by convex risk minimization,”IEEE Transactions on Information Theory, vol. 56, no. 11, pp. 5847–5861, 2010

    work page 2010

  55. [55]

    Generalization and equilibrium in generative adversarial nets (GANs),

    S. Arora, R. Ge, Y . Liang, T. Ma, and Y . Zhang, “Generalization and equilibrium in generative adversarial nets (GANs),” in Proceedings of the 34th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research, D. Precup and Y . W. Teh, Eds., vol. 70. PMLR, Aug. 2017, pp. 224–232

    work page 2017

  56. [56]

    On the discrimination-generalization tradeoff in GANs,

    P. Zhang, Q. Liu, D. Zhou, T. Xu, and X. He, “On the discrimination-generalization tradeoff in GANs,” in6th International Conference on Learning Representations, Apr. 2018

    work page 2018

  57. [57]

    Mutual information neural estimation,

    M. I. Belghazi, A. Baratin, S. Rajeshwar, S. Ozair, Y . Bengio, A. Courville, and D. Hjelm, “Mutual information neural estimation,” inProceedings of the 35th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research, J. Dy and A. Krause, Eds., vol. 80. PMLR, Jul. 2018, pp. 531–540

    work page 2018

  58. [58]

    Non-asymptotic performance guarantees for neural estimation of f-divergences,

    S. Sreekumar, Z. Zhang, and Z. Goldfeld, “Non-asymptotic performance guarantees for neural estimation of f-divergences,” inProceedings of the 24th International Conference on Artificial Intelligence and Statistics, vol. 130, Apr. 2021, pp. 3322–3330

    work page 2021

  59. [59]

    Neural estimation of statistical divergences,

    S. Sreekumar and Z. Goldfeld, “Neural estimation of statistical divergences,”Journal of Machine Learning Research, vol. 23, no. 126, pp. 1–75, 2022

    work page 2022

  60. [60]

    Variational representations and neural network estimation of R ´enyi divergences,

    J. Birrell, P. Dupuis, M. A. Katsoulakis, L. Rey-Bellet, and J. Wang, “Variational representations and neural network estimation of R ´enyi divergences,”SIAM Journal on Mathematics of Data Science, vol. 3, no. 4, pp. 1093–1116, 2021

    work page 2021

  61. [61]

    Variational quantum algorithms to estimate rank, quantum entropies, fidelity, and Fisher information via purity minimization,

    K. C. Tan and T. V olkoff, “Variational quantum algorithms to estimate rank, quantum entropies, fidelity, and Fisher information via purity minimization,”Physical Review Research, vol. 3, p. 033251, Sep 2021

    work page 2021

  62. [62]

    Estimating quantum mutual information through a quantum neural network,

    M. Shin, J. Lee, and K. Jeong, “Estimating quantum mutual information through a quantum neural network,”Quantum Information Processing, vol. 23, 02 2024

    work page 2024

  63. [63]

    Barren plateaus in quantum neural network training landscapes,

    J. R. McClean, S. Boixo, V . N. Smelyanskiy, R. Babbush, and H. Neven, “Barren plateaus in quantum neural network training landscapes,”Nature Communications, vol. 9, no. 1, p. 4812, Nov. 2018

    work page 2018

  64. [64]

    Cost-function-dependent barren plateaus in shallow parameterized quantum circuits,

    M. Cerezo, A. Sone, T. V olkoff, L. Cincio, and P. J. Coles, “Cost-function-dependent barren plateaus in shallow parameterized quantum circuits,”Nature Communications, vol. 12, p. 1791, 2021

    work page 2021

  65. [65]

    Connecting ansatz expressibility to gradient magnitudes and barren plateaus,

    Z. Holmes, K. Sharma, M. Cerezo, and P. J. Coles, “Connecting ansatz expressibility to gradient magnitudes and barren plateaus,”PRX Quantum, vol. 3, no. 1, p. 010313, 2022

    work page 2022

  66. [66]

    Exploiting symmetry in variational quantum machine learning,

    J. J. Meyer, M. Mularski, E. Gil-Fuster, A. A. Mele, F. Arzani, A. Wilms, and J. Eisert, “Exploiting symmetry in variational quantum machine learning,”PRX Quantum, vol. 4, no. 1, p. 010328, 2023

    work page 2023

  67. [67]

    Theory for equivariant quantum neural networks,

    Q. T. Nguyen, L. Schatzki, P. Braccia, M. Ragone, P. J. Coles, F. Sauvage, M. Larocca, and M. Cerezo, “Theory for equivariant quantum neural networks,”PRX Quantum, vol. 5, no. 2, p. 020328, 2024

    work page 2024

  68. [68]

    An initialization strategy for addressing barren plateaus in parameterized quantum circuits,

    E. Grant, L. Wossnig, M. Ostaszewski, and M. Benedetti, “An initialization strategy for addressing barren plateaus in parameterized quantum circuits,”Quantum, vol. 3, p. 214, 2019

    work page 2019

  69. [69]

    Layerwise learning for quantum neural networks,

    A. Skolik, J. R. McClean, M. Mohseni, P. van der Smagt, and M. Leib, “Layerwise learning for quantum neural networks,” Quantum Machine Intelligence, vol. 3, no. 1, pp. 1–19, 2021

    work page 2021

  70. [70]

    Does provable absence of barren plateaus imply classical simulability?

    M. Cerezo, M. Larocca, D. Garc ´ıa-Mart´ın, N. L. Diaz, P. Braccia, E. Fontana, M. S. Rudolph, P. Bermejo, A. Ijaz, S. Thanasilp, E. R. Anschuetz, and Z. Holmes, “Does provable absence of barren plateaus imply classical simulability?” Nature Communications, vol. 16, p. 7907, 2025

    work page 2025

  71. [71]

    Distinguishability and accessible information in quantum theory,

    C. Fuchs, “Distinguishability and accessible information in quantum theory,” Ph.D. dissertation, University of New Mexico, December 1996. 46

    work page 1996

  72. [72]

    Semi-definite optimization of the measured relative entropies of quantum states and channels,

    Z. Huang and M. M. Wilde, “Semi-definite optimization of the measured relative entropies of quantum states and channels,” arXiv: 2406.19060, 2025

    work page arXiv 2025

  73. [73]

    Estimation of entropy and mutual information,

    L. Paninski, “Estimation of entropy and mutual information,”Neural Computation, vol. 15, no. 6, p. 1191–1253, Jun. 2003

    work page 2003

  74. [74]

    Min- and max-relative entropies and a new entanglement monotone,

    N. Datta, “Min- and max-relative entropies and a new entanglement monotone,”IEEE Transactions on Information Theory, vol. 55, pp. 2816 – 2826, 07 2009

    work page 2009

  75. [75]

    The quantum Schur and Clebsch–Gordan transforms: I. efficient qudit circuits,

    D. Bacon, I. L. Chuang, and A. W. Harrow, “The quantum Schur and Clebsch–Gordan transforms: I. efficient qudit circuits,” inProceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, ser. SODA ’07. USA: Society for Industrial and Applied Mathematics, 2007, p. 1235–1244

    work page 2007

  76. [76]

    Applications of coherent classical communication and the Schur transform to quantum information theory

    A. W. Harrow, “Applications of coherent classical communication and the Schur transform to quantum information theory,” Ph.D. dissertation, Massachusetts Institute of Technology, Dec. 2005. [Online]. Available: https://arxiv.org/pdf/quant-ph/0512255

    work page internal anchor Pith review Pith/arXiv arXiv 2005

  77. [77]

    A practical quantum algorithm for the Schur transform,

    W. M. Kirby and F. W. Strauch, “A practical quantum algorithm for the Schur transform,”Quantum Information and Computation, vol. 18, no. 9-10, pp. 0721–0742, 2018

    work page 2018

  78. [78]

    An efficient high dimensional quantum Schur transform,

    H. Krovi, “An efficient high dimensional quantum Schur transform,”Quantum, vol. 3, p. 122, Feb. 2019

    work page 2019

  79. [79]

    ε-entropy andε-capacity of sets in functional spaces,

    V . M. Tikhomirov, “ε-entropy andε-capacity of sets in functional spaces,” inSelected works of AN Kolmogorov. Springer, 1993, pp. 86–170

    work page 1993

  80. [80]

    A. W. van der Vaart and J. A. Wellner,Weak Convergence and Empirical Processes. Springer, New York, 1996

    work page 1996

Showing first 80 references.