pith. sign in

arxiv: 2508.04486 · v2 · submitted 2025-08-06 · 🪐 quant-ph · cond-mat.dis-nn· cs.CC· cs.IT· cs.LG· math.IT

Quantum circuit complexity and unsupervised machine learning of topological order

Yanming Che , Clemens Gneiting , Xiaoguang Wang , Franco Nori This is my paper

Pith reviewed 2026-05-19 00:24 UTC · model grok-4.3

classification 🪐 quant-ph cond-mat.dis-nncs.CCcs.ITcs.LGmath.IT
keywords quantum circuit complexitytopological orderunsupervised machine learningmanifold learningquantum many-body systemsBures distanceentanglement generationquantum phases
0
0 comments X

The pith

Nielsen's quantum circuit complexity serves as an intrinsic topological distance between quantum many-body phases, enabling interpretable unsupervised manifold learning of topological order.

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

The paper argues that Nielsen's quantum circuit complexity measures an intrinsic topological distance between different phases of matter in quantum many-body systems. This distance underpins the design of practical similarity measures or kernels based on fidelity and entanglement generation, which are easier to compute than the full circuit complexity. These kernels are applied in unsupervised manifold learning to identify topological orders in models such as the bond-alternating XXZ spin chain and Kitaev's toric code, where they outperform standard approaches. The entanglement-based kernel proves especially robust against local noise because it captures long-range entanglement structures. The work also links these ideas to classical shadow tomography and shadow kernel learning.

Core claim

Nielsen's quantum circuit complexity represents an intrinsic topological distance between topological quantum many-body phases of matter and plays a central role in interpretable manifold learning of topological order. Two theorems connect this complexity for paths between arbitrary many-body states to quantum Fisher complexity via Bures distance and to entanglement generation. These connections allow formulation of fidelity-based and entanglement-based kernels that are used for unsupervised learning on the bond-alternating XXZ spin chain, the ground state of Kitaev's toric code, and random product states, demonstrating superior performance, with the entanglement approach being more robust.

What carries the argument

Nielsen's quantum circuit complexity, connected by two theorems to Bures distance and entanglement generation to form practical fidelity and entanglement kernels for manifold learning.

If this is right

  • Fidelity-based and entanglement-based kernels become usable practical substitutes for direct circuit complexity calculations in learning tasks.
  • Unsupervised learning successfully identifies topological order in the bond-alternating XXZ spin chain and Kitaev toric code ground states.
  • The entanglement-based kernel captures long-range entanglement and remains effective under local Haar random noise.
  • The approach naturally relates to classical shadow tomography and can explain shadow kernel learning.

Where Pith is reading between the lines

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

  • The same distance idea could be tested on other quantum phases such as symmetry-protected topological phases or many-body localized systems to see if circuit complexity still separates them.
  • Hybrid quantum-classical algorithms might compute the approximate kernels directly on quantum hardware for larger system sizes than classical simulation allows.
  • Traditional order parameters could be supplemented or replaced by complexity-based distances in phase diagrams of new materials.

Load-bearing premise

The two theorems that link or bound Nielsen circuit complexity to Bures distance and entanglement generation hold with enough accuracy for the many-body states of interest so that the resulting kernels still preserve topological distinctions.

What would settle it

If applying the fidelity-based or entanglement-based kernels to manifold learning on the Kitaev toric code ground state versus random product states fails to separate the known topological phase from the trivial ones, the central claim would be falsified.

Figures

Figures reproduced from arXiv: 2508.04486 by Clemens Gneiting, Franco Nori, Xiaoguang Wang, Yanming Che.

Figure 1
Figure 1. Figure 1: Landscape of machine learning topological phases of matter. Supervised learning requires prior information or labels, whose efficiency guarantees have been extensively investigated [36–45]. Under the constraint of geometric local￾ity [37, 39] or with bounded number (No.) of parameters (param.) [38], provably efficient machine learning of quantum many￾body systems has been established, e.g., in the framewor… view at source ↗
Figure 2
Figure 2. Figure 2: Unsupervised machine learning of the bond-alternating XXZ qubit chain with fidelity- and entanglement￾based kernels. (a) and (b) show the fidelity- and entanglement-based kernels, KF (ρ, ρ˜) and KE (ρ, ρ˜), respectively. One sees clearly three clusters in the heat map, corresponding to three distinct quantum phases of the model (trivial, symmetry broken, and topological) in a range of the model parameter J… view at source ↗
Figure 3
Figure 3. Figure 3: Unsupervised clustering of the ground state of Kitaev’s toric code (blue dots) and random product states (RPS) (red dots) without or with applying two-qubit random unitaries, via fidelity- and entanglement-based kernels, respec￾tively. (a) and (b) show a one-dimensional (1D) representation of the data set in terms of the kernel’s principal components (i.e., via the algorithm of kernel PCA with shifting the… view at source ↗
Figure 4
Figure 4. Figure 4: Unsupervised clustering of the ground state of the extended toric code (ETC) (blue dots) and random product states (RPS) (red dots) without or with applying local perturbations, via fidelity- and entanglement-based kernels, re￾spectively. (a) and (b) show a one-dimensional (1D) representation of the data set in terms of the kernel’s principal components (i.e., via the algorithm of kernel PCA with shifting … view at source ↗
read the original abstract

Inspired by the close relationship between Kolmogorov complexity and unsupervised machine learning, we explore quantum circuit complexity, an important concept in quantum computation and quantum information science, as a pivot to understand and to build interpretable and efficient unsupervised machine learning for topological order in quantum many-body systems. We argue that Nielsen's quantum circuit complexity represents an intrinsic topological distance between topological quantum many-body phases of matter, and as such plays a central role in interpretable manifold learning of topological order. To span a bridge from conceptual power to practical applicability, we present two theorems that connect Nielsen's quantum circuit complexity for the quantum path planning between two arbitrary quantum many-body states with quantum Fisher complexity (Bures distance) and entanglement generation, respectively. Leveraging these connections, fidelity-based and entanglement-based similarity measures or kernels, which are more practical for implementation, are formulated. Using the two proposed distance measures, unsupervised manifold learning of quantum phases of the bond-alternating XXZ spin chain, the ground state of Kitaev's toric code and random product states, is conducted, demonstrating their superior performance. Moreover, we find that the entanglement-based approach, which captures the long-range structure of quantum entanglement of topological orders, is more robust to local Haar random noises. Relations with classical shadow tomography and shadow kernel learning are also discussed, where the latter can be naturally understood from our approach. Our results establish connections between key concepts and tools of quantum circuit computation, quantum complexity, quantum metrology, and machine learning of topological quantum order.

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

1 major / 2 minor

Summary. The paper argues that Nielsen's quantum circuit complexity represents an intrinsic topological distance between quantum many-body phases and can serve as a pivot for interpretable unsupervised manifold learning of topological order. It presents two theorems connecting Nielsen complexity for paths between arbitrary states to Bures distance (via quantum Fisher information) and to entanglement generation, respectively. These are used to construct practical fidelity-based and entanglement-based kernels, which are then applied to unsupervised learning on the bond-alternating XXZ chain, Kitaev toric code ground states, and random product states, with reported superior performance and greater robustness of the entanglement kernel to local Haar noise. Relations to classical shadow tomography and shadow kernel learning are discussed.

Significance. If the theorems hold with sufficient accuracy for the relevant many-body states and the resulting kernels preserve topological distinctions, the work would establish a conceptually grounded link between quantum circuit complexity, quantum metrology, and machine learning of topological phases, potentially offering more interpretable alternatives to standard distance measures in phase classification tasks.

major comments (1)
  1. [Theorems (abstract and main development)] Theorems connecting Nielsen complexity to Bures distance and entanglement generation (stated in the abstract and developed in the main text): these are presented for arbitrary states, but the manuscript supplies no explicit error bounds, approximation accuracy estimates, or finite-size scaling analysis to verify that the derived fidelity- and entanglement-based kernels retain long-range topological information rather than generic state features in the regimes of the numerical examples (bond-alternating XXZ, toric code). This is load-bearing for the central claim that the kernels enable manifold learning of topological order.
minor comments (2)
  1. [Numerical results section] The numerical demonstrations would be strengthened by explicit quantitative comparisons (e.g., clustering accuracy, silhouette scores) against standard baselines such as PCA or other kernel methods, rather than qualitative statements of 'superior performance'.
  2. [Kernel definitions] Notation for the kernels and distance measures could be clarified with a dedicated table or explicit definitions early in the text to aid readability for readers outside quantum complexity.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their careful reading and constructive feedback. We address the single major comment below, providing a point-by-point response while committing to targeted revisions that strengthen the presentation without altering the core claims.

read point-by-point responses

  1. Referee: Theorems connecting Nielsen complexity to Bures distance and entanglement generation (stated in the abstract and developed in the main text): these are presented for arbitrary states, but the manuscript supplies no explicit error bounds, approximation accuracy estimates, or finite-size scaling analysis to verify that the derived fidelity- and entanglement-based kernels retain long-range topological information rather than generic state features in the regimes of the numerical examples (bond-alternating XXZ, toric code). This is load-bearing for the central claim that the kernels enable manifold learning of topological order.

    Authors: The two theorems are exact identities that follow directly from the definitions of Nielsen complexity, the quantum Fisher information metric, and entanglement entropy; they hold for arbitrary states with no approximation or truncation. Consequently, error bounds on the theorems themselves are unnecessary. The fidelity- and entanglement-based kernels are obtained by substituting the exact relations into practical similarity measures. In the numerical examples we deliberately chose models (bond-alternating XXZ chain and Kitaev toric code) whose topological phases are independently established by order parameters and entanglement spectra. The observed phase clustering and the entanglement kernel’s superior robustness under local Haar noise indicate that long-range topological structure is being captured rather than short-range generic features. We nevertheless agree that an explicit finite-size scaling study would further substantiate this point. In the revised manuscript we will add (i) performance metrics versus system size for the XXZ chain and (ii) a brief discussion of how the kernels’ ability to separate topological sectors scales toward the thermodynamic limit. revision: partial

Circularity Check

0 steps flagged

No significant circularity; derivations are self-contained

full rationale

The paper derives two theorems connecting Nielsen circuit complexity to Bures distance and entanglement generation for arbitrary states, then applies the resulting fidelity and entanglement kernels to manifold learning on concrete models (bond-alternating XXZ, toric code, random products). These steps are presented as independent mathematical connections rather than fits or self-referential definitions; the topological-distance claim is argued conceptually from the theorems and validated by explicit demonstrations, without any reduction of a central prediction to a fitted parameter or prior self-citation by construction. The work remains self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The central claim rests on standard quantum-information axioms (unitary evolution, definition of Nielsen complexity, Bures metric, and entanglement measures) without introducing new free parameters or postulated entities in the abstract description.

axioms (2)
  • standard math Nielsen's geometric formulation of quantum circuit complexity is well-defined for the many-body states considered.
    Invoked when treating complexity as an intrinsic distance.
  • domain assumption The Bures distance and entanglement generation are independent quantities that can be related to circuit complexity via the stated theorems.
    Basis for the two practical kernels.

pith-pipeline@v0.9.0 · 5820 in / 1546 out tokens · 50955 ms · 2026-05-19T00:24:35.640738+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

106 extracted references · 106 canonical work pages · 6 internal anchors

  1. [1]

    Colloquium: Topological insulators,

    M. Z. Hasan and C. L. Kane, “Colloquium: Topological insulators,” Rev. Mod. Phys. 82, 3045–3067 (2010)

    work page 2010

  2. [2]

    Topological insulators and superconductors,

    X.-L. Qi and S.-C. Zhang, “Topological insulators and superconductors,” Rev. Mod. Phys.83, 1057–1110 (2011)

    work page 2011

  3. [3]

    Gapped quantum liquids and topological order, stochastic local transformations and emergence of unitarity,

    B. Zeng and X.-G. Wen, “Gapped quantum liquids and topological order, stochastic local transformations and emergence of unitarity,” Phys. Rev. B91, 125121 (2015)

    work page 2015

  4. [4]

    Quantum Information Meets Quantum Matter -- From Quantum Entanglement to Topological Phase in Many-Body Systems

    B. Zeng, X. Chen, D.-L. Zhou, and X.-G. Wen, “Quantum Information Meets Quantum Matter – From Quantum Entanglement to Topological Phase in Many-Body Systems,” arxiv:1508.02595 (2015)

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  5. [5]

    Topological entanglement entropy,

    A. Kitaev and J. Preskill, “Topological entanglement entropy,” Phys. Rev. Lett.96, 110404 (2006)

    work page 2006

  6. [6]

    Detecting topological order in a ground state wave function,

    M. Levin and X.-G. Wen, “Detecting topological order in a ground state wave function,” Phys. Rev. Lett. 96, 110405 (2006)

    work page 2006

  7. [7]

    Fault-tolerant quantum computation by anyons,

    A. Yu. Kitaev, “Fault-tolerant quantum computation by anyons,” Annals of Physics303, 2–30 (2003)

    work page 2003

  8. [8]

    Probing topological spin liquids on a programmable quantum simulator,

    G. Semeghini et al., “Probing topological spin liquids on a programmable quantum simulator,” Science374, 1242–1247 (2021)

    work page 2021

  9. [9]

    Realizing topologically ordered states on a quantum processor,

    K. J. Satzinger et al., “Realizing topologically ordered states on a quantum processor,” Science374, 1237–1241 (2021)

    work page 2021

  10. [10]

    Quantum error correction below the surface code threshold.Nature, 638:920–926, 2025

    Google Quantum AI and Collaborators, “Quantum error correction below the surface code threshold,” Nature (2024), 10.1038/s41586-024-08449-y

    work page doi:10.1038/s41586-024-08449-y 2024

  11. [11]

    Solving the quantum many-body problem with artificial neural networks,

    G. Carleo and M. Troyer, “Solving the quantum many-body problem with artificial neural networks,” Science 355, 602–606 (2017)

    work page 2017

  12. [12]

    Machine learning phases of matter,

    J. Carrasquilla and R. G. Melko, “Machine learning phases of matter,” Nat. Phys. 13, 431 (2017)

    work page 2017

  13. [13]

    Learning phase transitions by confusion,

    E. P. L. Van Nieuwenburg, Y .-H. Liu, and S. D. Huber, “Learning phase transitions by confusion,” Nat. Phys. 13, 435 (2017)

    work page 2017

  14. [14]

    Quantum Loop Topography for Machine Learning,

    Y . Zhang and E.-A. Kim, “Quantum Loop Topography for Machine Learning,” Phys. Rev. Lett.118, 216401 (2017)

    work page 2017

  15. [15]

    Discriminative Cooperative Networks for Detecting Phase Transitions,

    Y .-H. Liu and E. P. L. van Nieuwenburg, “Discriminative Cooperative Networks for Detecting Phase Transitions,” Phys. Rev. Lett. 120, 176401 (2018). 15

    work page 2018

  16. [16]

    Machine Learning Topological Invariants with Neural Networks,

    P. Zhang, H. Shen, and H. Zhai, “Machine Learning Topological Invariants with Neural Networks,” Phys. Rev. Lett. 120, 066401 (2018)

    work page 2018

  17. [17]

    Deep learning topological invariants of band insulators,

    N. Sun, J. Yi, P. Zhang, H. Shen, and H. Zhai, “Deep learning topological invariants of band insulators,” Phys. Rev. B 98, 085402 (2018)

    work page 2018

  18. [18]

    Machine learning and the physical sciences,

    G. Carleo, I. Cirac, K. Cranmer, L. Daudet, M. Schuld, N. Tishby, L. V ogt-Maranto, and L. Zdeborov ´a, “Machine learning and the physical sciences,” Rev. Mod. Phys.91, 045002 (2019)

    work page 2019

  19. [19]

    Quantum topology identification with deep neural networks and quantum walks,

    Y . Ming, C.-T. Lin, S. D Bartlett, and W.-W. Zhang, “Quantum topology identification with deep neural networks and quantum walks,” npj Computational Materials5, 1–7 (2019)

    work page 2019

  20. [20]

    Identi- fying quantum phase transitions using artificial neural networks on experimental data,

    B. S. Rem, N. K ¨aming, M. Tarnowski, L. Asteria, N. Fl¨aschner, C. Becker, K. Sengstock, and C. Weitenberg, “Identi- fying quantum phase transitions using artificial neural networks on experimental data,” Nat. Phys.15, 917–920 (2019)

    work page 2019

  21. [21]

    Machine Learning Topological Phases with a Solid-State Quantum Simulator,

    W. Lian, S.-T. Wang, S. Lu, Y . Huang, F. Wang, X. Yuan, W. Zhang, X. Ouyang, X. Wang, X. Huang, L. He, X. Chang, D.-L. Deng, and L. Duan, “Machine Learning Topological Phases with a Solid-State Quantum Simulator,” Phys. Rev. Lett. 122, 210503 (2019)

    work page 2019

  22. [22]

    Identifying topological order through unsupervised machine learning,

    J. F. Rodriguez-Nieva and M. S. Scheurer, “Identifying topological order through unsupervised machine learning,” Nat. Phys. 15, 790–795 (2019)

    work page 2019

  23. [23]

    Topological quantum phase transitions retrieved through unsupervised ma- chine learning,

    Y . Che, C. Gneiting, T. Liu, and F. Nori, “Topological quantum phase transitions retrieved through unsupervised ma- chine learning,” Phys. Rev. B102, 134213 (2020)

    work page 2020

  24. [24]

    Unsupervised Machine Learning and Band Topology,

    M. S. Scheurer and R.-J. Slager, “Unsupervised Machine Learning and Band Topology,” Phys. Rev. Lett. 124, 226401 (2020)

    work page 2020

  25. [25]

    Unsupervised Manifold Clustering of Topological Phononics,

    Y . Long, J. Ren, and H. Chen, “Unsupervised Manifold Clustering of Topological Phononics,” Phys. Rev. Lett. 124, 185501 (2020)

    work page 2020

  26. [26]

    Unsupervised identification of topological phase transitions using predictive models,

    E. Greplova, A. Valenti, G. Boschung, F. Sch¨afer, N. L¨orch, and S. D. Huber, “Unsupervised identification of topological phase transitions using predictive models,” New Journal of Physics22, 045003 (2020)

    work page 2020

  27. [27]

    Unsupervised learning using topological data augmentation,

    O. Balabanov and M. Granath, “Unsupervised learning using topological data augmentation,” Phys. Rev. Res.2, 013354 (2020)

    work page 2020

  28. [28]

    Unsupervised Learning of Non-Hermitian Topological Phases,

    L.-W. Yu and D.-L. Deng, “Unsupervised Learning of Non-Hermitian Topological Phases,” Phys. Rev. Lett.126, 240402 (2021)

    work page 2021

  29. [29]

    Unsupervised learning universal critical behavior via the intrinsic dimension,

    T. Mendes-Santos, X. Turkeshi, M. Dalmonte, and A. Rodriguez, “Unsupervised learning universal critical behavior via the intrinsic dimension,” Phys. Rev. X11, 011040 (2021)

    work page 2021

  30. [30]

    Topological data analysis and machine learning,

    D. Leykam and D. G. Angelakis, “Topological data analysis and machine learning,” Advances in Physics: X8, 2202331 (2023)

    work page 2023

  31. [31]

    Identifying topology of leaky photonic lattices with machine learning,

    E. Smolina, L. Smirnov, D. Leykam, F. Nori, and D. Smirnova, “Identifying topology of leaky photonic lattices with machine learning,” Nanophotonics13, 271–281 (2024)

    work page 2024

  32. [32]

    Machine learning meets quantum physics,

    S. Das Sarma, D.-L. Deng, and L.-M. Duan, “Machine learning meets quantum physics,” Physics Today 72, 48–54 (2019)

    work page 2019

  33. [33]

    A theory of the learnable,

    L. G. Valiant, “A theory of the learnable,” Communications of the ACM27, 1134–1142 (1984)

    work page 1984

  34. [34]

    Mohri, A

    M. Mohri, A. Rostamizadeh, and A. Talwalkar, Foundations of Machine Learning, 2nd ed., Adaptive Computation and Machine Learning (MIT Press, Cambridge, MA, USA, 2018)

    work page 2018

  35. [35]

    Neural tangent kernel: Convergence and generalization in neural networks,

    A. Jacot, F. Gabriel, and C. Hongler, “Neural tangent kernel: Convergence and generalization in neural networks,” in Advances in Neural Information Processing Systems, V ol. 31, edited by S. Bengioet. al. (Curran Associates, Inc., 2018) pp. 8571–8580

    work page 2018

  36. [36]

    Provably efficient machine learning for quantum many-body problems,

    H.-Y . Huang, R. Kueng, G. Torlai, V . V . Albert, and J. Preskill, “Provably efficient machine learning for quantum many-body problems,” Science377, eabk3333 (2022)

    work page 2022

  37. [37]

    Improved machine learning algorithm for predicting ground state properties,

    L. Lewis, H.-Y . Huang, V . T. Tran, S. Lehner, R. Kueng, and J. Preskill, “Improved machine learning algorithm for predicting ground state properties,” Nat. Commun.15, 895 (2024)

    work page 2024

  38. [38]

    Exponentially improved efficient machine learning for quantum many-body states with provable guarantees,

    Y . Che, C. Gneiting, and F. Nori, “Exponentially improved efficient machine learning for quantum many-body states with provable guarantees,” Phys. Rev. Res.6, 033035 (2024)

    work page 2024

  39. [39]

    Efficient learning of ground and thermal states within phases of matter,

    C. Rouz ´e, D. Stilck Franc ¸a, E. Onorati, and J. D. Watson, “Efficient learning of ground and thermal states within phases of matter,” Nat. Commun.15, 7755 (2024)

    work page 2024

  40. [40]

    Machine learning on quantum experimental data toward solving quantum many-body problems,

    G. Cho and D. Kim, “Machine learning on quantum experimental data toward solving quantum many-body problems,” Nat. Commun. 15, 7552 (2024)

    work page 2024

  41. [41]

    Learning Quantum States and Unitaries of Bounded Gate Complexity,

    H. Zhao, L. Lewis, I. Kannan, Y . Quek, H.-Y . Huang, and M. C. Caro, “Learning Quantum States and Unitaries of Bounded Gate Complexity,” PRX Quantum5, 040306 (2024)

    work page 2024

  42. [42]

    Provably efficient learning of phases of matter via dissipative evolutions,

    E. Onorati, C. Rouz´e, D. Stilck Franc ¸a, , and J. D. Watson, “Provably efficient learning of phases of matter via dissipative evolutions,” arxiv:2311.07506 (2023)

    work page arXiv 2023

  43. [43]

    Efficient learning for linear properties of bounded-gate quantum circuits,

    Y . Du, M.-H. Hsieh, and D. Tao, “Efficient learning for linear properties of bounded-gate quantum circuits,” arxiv:2408.12199 (2024)

    work page arXiv 2024

  44. [44]

    Predicting ground state properties: Constant sample complexity and deep learning algorithms,

    M. Wanner, L. Lewis, C. Bhattacharyya, D. Dubhashi, and A. Gheorghiu, “Predicting ground state properties: Constant sample complexity and deep learning algorithms,” arxiv:2405.18489 (2024)

    work page arXiv 2024

  45. [45]

    Efficient learning of long-range and equivariant quantum systems,

    ˇS. ˇSm´ıd and R. Bondesan, “Efficient learning of long-range and equivariant quantum systems,” arxiv:2312.17019 (2023)

    work page arXiv 2023

  46. [46]

    Nonlinear component analysis as a kernel eigenvalue problem,

    B. Sch ¨olkopf, A. Smola, and K.-R. M ¨uller, “Nonlinear component analysis as a kernel eigenvalue problem,” Neural Computation 10, 1299–1319 (1998)

    work page 1998

  47. [47]

    Kernel PCA and de-noising in feature spaces,

    S. Mika, B. Sch ¨olkopf, A. Smola, K.-R. M ¨uller, M. Scholz, and G. R ¨atsch, “Kernel PCA and de-noising in feature spaces,” in Advances in Neural Information Processing Systems , V ol. 11, edited by M. Kearns, S. Solla, and D. Cohn (MIT Press, Cambridge, MA, 1999) pp. 536–542. 16

    work page 1999

  48. [48]

    Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps,

    R. R. Coifman, S. Lafon, A. B. Lee, M. Maggioni, B. Nadler, F. Warner, and S. W. Zucker, “Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps,” Proc. Natl. Acad. Sci. U.S.A. 102, 7426–7431 (2005)

    work page 2005

  49. [49]

    Diffusion maps, spectral clustering and eigenfunctions of Fokker-Planck operators,

    B. Nadler, S. Lafon, I. Kevrekidis, and R. R. Coifman, “Diffusion maps, spectral clustering and eigenfunctions of Fokker-Planck operators,” inAdvances in neural information processing systems (2006) pp. 955–962

    work page 2006

  50. [50]

    Unsupervised Data-Driven Classification of Topological Gapped Systems with Symmetries,

    Y . Long and B. Zhang, “Unsupervised Data-Driven Classification of Topological Gapped Systems with Symmetries,” Phys. Rev. Lett. 130, 036601 (2023)

    work page 2023

  51. [51]

    Undecidability of the spectral gap,

    T. S. Cubitt, D. Perez-Garcia, and M. M. Wolf, “Undecidability of the spectral gap,” Nature 528, 207–211 (2015)

    work page 2015

  52. [52]

    Information Distance

    C. H. Bennett, P. G ´acs, M. Li, Paul M. B. Vit´anyi, and W. H. Zurek, “Information distance,” arxiv:1006.3520 (2010)

    work page internal anchor Pith review Pith/arXiv arXiv 2010

  53. [53]

    The idea that the conditional Kolmogorov complexity K(x|y) provides a theoretically optimal solution to unsupervised machine learning was, to the best of our knowledge, first formulated in a talk by Ilya Sutskever

    work page

  54. [54]

    Quantum circuit complexity,

    A. Chi-Chih Yao, “Quantum circuit complexity,” in Proceedings of 1993 IEEE 34th Annual Foundations of Computer Science (1993) pp. 352–361

    work page 1993

  55. [55]

    Models of quantum complexity growth,

    Fernando G.S.L. Brand ˜ao, W. Chemissany, N. Hunter-Jones, R. Kueng, and J. Preskill, “Models of quantum complexity growth,” PRX Quantum2, 030316 (2021)

    work page 2021

  56. [56]

    Linear growth of quantum circuit complexity,

    J. Haferkamp, P. Faist, N. B. T. Kothakonda, J. Eisert, and N. Yunger Halpern, “Linear growth of quantum circuit complexity,” Nat. Phys.18, 528–532 (2022)

    work page 2022

  57. [57]

    Complexity and order in approximate quantum error-correcting codes,

    J. Yi, W. Ye, D. Gottesman, and Z.-W. Liu, “Complexity and order in approximate quantum error-correcting codes,” Nat. Phys. 20, 1798–1803 (2024)

    work page 2024

  58. [58]

    Circuit complexity across a topological phase transition,

    F. Liu, S. Whitsitt, J. B. Curtis, R. Lundgren, P. Titum, Z.-C. Yang, J. R. Garrison, and A. V . Gorshkov, “Circuit complexity across a topological phase transition,” Phys. Rev. Res.2, 013323 (2020)

    work page 2020

  59. [59]

    Toward a Definition of Complexity for Quantum Field Theory States,

    S. Chapman, M. P. Heller, H. Marrochio, and F. Pastawski, “Toward a Definition of Complexity for Quantum Field Theory States,” Phys. Rev. Lett.120, 121602 (2018)

    work page 2018

  60. [60]

    Circuit complexity for free fermions,

    L. Hackl and R. C. Myers, “Circuit complexity for free fermions,” J. High Energ. Phys. 2018, 139 (2018)

    work page 2018

  61. [61]

    Circuit complexity in fermionic field theory,

    R. Khan, C. Krishnan, and S. Sharma, “Circuit complexity in fermionic field theory,” Phys. Rev. D 98, 126001 (2018)

    work page 2018

  62. [62]

    Computational Complexity and Black Hole Horizons

    L. Susskind, “Computational Complexity and Black Hole Horizons,” arxiv:1402.5674 (2014)

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  63. [63]

    Complexity and shock wave geometries,

    D. Stanford and L. Susskind, “Complexity and shock wave geometries,” Phys. Rev. D90, 126007 (2014)

    work page 2014

  64. [64]

    Holographic Complexity Equals Bulk Action?

    A. R. Brown, D. A. Roberts, L. Susskind, B. Swingle, and Y . Zhao, “Holographic Complexity Equals Bulk Action?” Phys. Rev. Lett. 116, 191301 (2016)

    work page 2016

  65. [65]

    Complexity, action, and black holes,

    A. R. Brown, D. A. Roberts, L. Susskind, B. Swingle, and Y . Zhao, “Complexity, action, and black holes,” Phys. Rev. D 93, 086006 (2016)

    work page 2016

  66. [66]

    Universality in long-distance geometry and quantum complexity,

    A. R. Brown, M. H. Freedman, H. W. Lin, and L. Susskind, “Universality in long-distance geometry and quantum complexity,” Nature622, 58–62 (2023)

    work page 2023

  67. [67]

    Automorphic Equivalence within Gapped Phases of Quantum Lattice Systems,

    S. Bachmann, S. Michalakis, B. Nachtergaele, and R. Sims, “Automorphic Equivalence within Gapped Phases of Quantum Lattice Systems,” Commun. Math. Phys.309, 835–871 (2012)

    work page 2012

  68. [68]

    A geometric approach to quantum circuit lower bounds

    M. A. Nielsen, “A geometric approach to quantum circuit lower bounds,” arxiv:quant-ph/0502070 (2005)

    work page internal anchor Pith review Pith/arXiv arXiv 2005

  69. [69]

    Quantum Computation as Geometry,

    M. A. Nielsen, M. R. Dowling, M. Gu, and A. C. Doherty, “Quantum Computation as Geometry,” Science 311, 1133–1135 (2006)

    work page 2006

  70. [70]

    Entangling Power and Quantum Circuit Complexity,

    J. Eisert, “Entangling Power and Quantum Circuit Complexity,” Phys. Rev. Lett. 127, 020501 (2021)

    work page 2021

  71. [71]

    M. A. Nielsen and I. L. Chuang, Quantum Computation and Quantum Information (Cambridge University Press, Cam- bridge, England, 2012)

    work page 2012

  72. [72]

    Statistical Distance and the Geometry of Quantum States,

    S. L. Braunstein and C. M. Caves, “Statistical Distance and the Geometry of Quantum States,” Phys. Rev. Lett.72, 3439 (1994)

    work page 1994

  73. [73]

    Quantum Fisher information matrix and multiparameter estimation,

    J. Liu, H. Yuan, X.-M. Lu, and X. Wang, “Quantum Fisher information matrix and multiparameter estimation,” J. Phys. A: Math. Theor. 53, 023001 (2020)

    work page 2020

  74. [74]

    Quantum Speed Limit for Physical Processes,

    M. M. Taddei, B. M. Escher, L. Davidovich, and R. L. de Matos Filho, “Quantum Speed Limit for Physical Processes,” Phys. Rev. Lett. 110, 050402 (2013)

    work page 2013

  75. [75]

    C. W. Helstrom, Quantum Detection and Estimation Theory (Academic Press, New York, 1976)

    work page 1976

  76. [76]

    A. S. Holevo, Probabilistic and Statistical Aspects of Quantum Theory (North-Holland Publishing Company, Amster- dam, 1982)

    work page 1982

  77. [77]

    Density matrix formulation for quantum renormalization groups,

    S. R. White, “Density matrix formulation for quantum renormalization groups,” Phys. Rev. Lett. 69, 2863 (1992)

    work page 1992

  78. [78]

    The density-matrix renormalization group in the age of matrix product states,

    U. Schollwoeck, “The density-matrix renormalization group in the age of matrix product states,” Annals of Physics326, 96 (2011)

    work page 2011

  79. [79]

    Predicting many properties of a quantum system from very few measurements,

    H.-Y . Huang, R. Kueng, and J. Preskill, “Predicting many properties of a quantum system from very few measurements,” Nat. Phys. 16, 1050–1057 (2020)

    work page 2020

  80. [80]

    Detection of symmetry-protected topological phases in one dimension,

    F. Pollmann and A. M. Turner, “Detection of symmetry-protected topological phases in one dimension,” Phys. Rev. B 86, 125441 (2012)

    work page 2012

Showing first 80 references.