pith. sign in

arxiv: 2606.23652 · v1 · pith:NFAPFRAPnew · submitted 2026-06-22 · 🪐 quant-ph · cs.IT· cs.NA· math.IT· math.NA· math.ST· stat.TH

Robust Structure Learning of k-local Lindbladians

Tim M\"obus , Thiago Bergamaschi , Daniel Stilck Fran\c{c}a , Cambyse Rouz\'e This is my paper

Pith reviewed 2026-06-26 08:06 UTC · model grok-4.3

classification 🪐 quant-ph cs.ITcs.NAmath.ITmath.NAmath.STstat.TH
keywords Lindblad dynamicsstructure learningquantum tomographyopen quantum systemssample complexityPauli measurementsdissipative quantum systems
0
0 comments X

The pith

An efficient protocol learns k-local Lindblad generators to accuracy ε using Õ(n^{2k}) samples.

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

The paper develops a method to learn the full set of coefficients defining a k-local Lindblad generator, which describes the evolution of an open quantum system on n qubits. The approach relies solely on preparing product states, evolving for short times, and measuring single-qubit Paulis, without needing to know the interaction graph beforehand. It achieves entrywise accuracy epsilon on all coefficients using order n to the 2k over epsilon squared samples for fixed k and bounded strengths. A subsequent projection step ensures the output is a valid generator with diamond norm error at most epsilon, at the cost of n to the 4k samples. This opens the door to characterizing dissipative dynamics in many-body systems under realistic experimental constraints.

Core claim

We present an efficient protocol for learning an unknown k-local Lindblad generator on n qubits using only product-state preparations, short-time evolution, and single-qubit Pauli measurements, without prior knowledge of the interaction structure. For fixed k and bounded weighted interaction strength, the protocol estimates all Hamiltonian and dissipative Pauli--GKSL coefficients to entrywise accuracy ε with probability at least 1-δ using Õ_k(ε^{-2}n^{2k}log(1/δ)) samples and polylogarithmically many evolution times. A semidefinite projection converts these estimates into a valid k-local Lindblad generator with diamond-norm error at most ε using Õ_k(ε^{-2}n^{4k}log(1/δ)) samples and polynomi

What carries the argument

Estimation of Pauli-GKSL coefficients from short-time evolutions combined with semidefinite projection onto the set of valid Lindblad generators.

Load-bearing premise

The weighted interaction strength must be bounded independently of system size n, and k must remain fixed.

What would settle it

Finding a family of k-local Lindbladians where achieving epsilon accuracy on the coefficients requires substantially more than n to the 2k samples, such as exponential in k or worse polynomial dependence.

read the original abstract

We present an efficient protocol for learning an unknown $k$-local Lindblad generator on $n$ qubits using only product-state preparations, short-time evolution, and single-qubit Pauli measurements, without prior knowledge of the interaction structure. For fixed $k$ and bounded weighted interaction strength, the protocol estimates all Hamiltonian and dissipative Pauli--GKSL coefficients to entrywise accuracy $\varepsilon$ with probability at least $1-\delta$ using $\widetilde{\mathcal O}_k(\varepsilon^{-2}n^{2k}\log(1/\delta))$ samples and polylogarithmically many evolution times. A semidefinite projection converts these estimates into a valid $k$-local Lindblad generator with diamond-norm error at most $\varepsilon$ using $\widetilde{\mathcal O}_k(\varepsilon^{-2}n^{4k}\log(1/\delta))$ samples and polynomial-time classical postprocessing. If a suitable set of influential coefficients is supplied and satisfies a stable sparsity condition, the dependence on $n$ can improve from polynomial to logarithmic; in particular, exact supports of bounded intersection degree require only $\widetilde{\mathcal O}_k(\varepsilon^{-2}\log(n/\delta))$ samples, with analogous reductions in system-size dependence for sufficiently decaying long-range interactions. We also provide a robust structure-learning procedure, extend the guarantees to model misspecification, and prove complementary sample-complexity lower bounds. To our knowledge, these are the first efficient learning guarantees for general $k$-local dissipative quantum dynamics under such limited experimental control.

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 / 1 minor

Summary. The paper presents an efficient protocol for learning an unknown k-local Lindblad generator on n qubits from product-state preparations, short-time evolution, and single-qubit Pauli measurements, without prior knowledge of the interaction graph. Under the assumptions of fixed k and bounded weighted interaction strength, it claims entrywise estimation of all Hamiltonian and dissipative Pauli-GKSL coefficients to accuracy ε with Õ_k(ε^{-2} n^{2k} log(1/δ)) samples, followed by an SDP projection step achieving diamond-norm error ε with Õ_k(ε^{-2} n^{4k} log(1/δ)) samples. Extensions include robust structure learning under stable sparsity (reducing to Õ_k(ε^{-2} log(n/δ)) samples for bounded intersection degree), robustness to model misspecification, and matching lower bounds.

Significance. If the central claims and error analyses hold, the result would constitute a notable advance in quantum system identification for open systems, supplying the first polynomial-sample guarantees for general k-local dissipative dynamics under severely restricted experimental control (product states and local measurements only). The SDP projection to a valid generator and the structure-learning reductions under sparsity are technically substantive contributions.

major comments (2)
  1. [Abstract, §1] Abstract and §1: the sample-complexity statements are explicitly conditioned on bounded weighted interaction strength; the manuscript must clarify in which theorem this hypothesis is invoked to control truncation error in the short-time channel expansion and the variance of the Pauli estimators, and whether the SDP projection inherits the same dependence without additional factors.
  2. [Abstract] The semidefinite projection step (mentioned in abstract) converts coefficient estimates into a valid k-local Lindblad generator; the error analysis for this step must be checked against the entrywise ε guarantee to confirm the diamond-norm bound does not inflate the sample requirement beyond the stated Õ(n^{4k}).
minor comments (1)
  1. [Abstract] Notation for the weighted interaction strength should be defined at first use and its relation to the GKSL coefficients made explicit.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their careful reading and for highlighting these points on conditioning and error propagation. We address each major comment below and will incorporate clarifications where appropriate.

read point-by-point responses

  1. Referee: [Abstract, §1] Abstract and §1: the sample-complexity statements are explicitly conditioned on bounded weighted interaction strength; the manuscript must clarify in which theorem this hypothesis is invoked to control truncation error in the short-time channel expansion and the variance of the Pauli estimators, and whether the SDP projection inherits the same dependence without additional factors.

    Authors: The bounded weighted interaction strength assumption is stated in the abstract and invoked explicitly in Theorem 3.1 (entrywise coefficient estimation). It enters via Lemma 2.3 to bound truncation error in the short-time expansion and via Lemma 3.2 to control estimator variance. Theorem 4.1 (SDP projection) inherits the same dependence without extra polynomial factors in n or 1/ε, because the projection is 1-Lipschitz in the diamond norm under the bounded-strength hypothesis and the entrywise ε guarantee is already sufficient. We will add forward references to Theorems 3.1 and 4.1 in the abstract and §1. revision: yes

  2. Referee: [Abstract] The semidefinite projection step (mentioned in abstract) converts coefficient estimates into a valid k-local Lindblad generator; the error analysis for this step must be checked against the entrywise ε guarantee to confirm the diamond-norm bound does not inflate the sample requirement beyond the stated Õ(n^{4k}).

    Authors: Section 4 contains the full error analysis. The SDP projection maps an entrywise-ε estimate (under bounded strength) to a valid generator whose diamond-norm distance is at most ε; the proof uses contractivity of the projection together with the coefficient bounds already assumed for the entrywise stage. Consequently the sample complexity remains Õ_k(ε^{-2} n^{4k} log(1/δ)) and is not inflated. No revision to the stated bound is required. revision: no

Circularity Check

0 steps flagged

No significant circularity; derivation rests on standard concentration and SDP arguments

full rationale

The protocol derives sample bounds from Hoeffding-type concentration on single-qubit Pauli estimators and a subsequent SDP projection step, both under the explicit hypothesis of fixed k and bounded weighted interaction strength. No quoted step reduces a claimed prediction to a fitted parameter by construction, invokes a self-citation as the sole justification for a uniqueness or ansatz claim, or renames an empirical pattern. The central Õ(n^{2k}) bound follows directly from variance control on the short-time channel expansion and does not collapse to the input data or prior author results.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

Review based on abstract only. The protocol rests on domain assumptions of fixed locality k and bounded weighted interaction strength; no free parameters or invented entities are visible in the abstract. Full paper would likely invoke standard matrix concentration inequalities and SDP projection properties.

axioms (2)
  • domain assumption Fixed k (locality parameter)
    Sample complexity depends polynomially on k; stated for fixed k.
  • domain assumption Bounded weighted interaction strength
    Required for the Õ(n^{2k}) scaling to hold.

pith-pipeline@v0.9.1-grok · 5834 in / 1315 out tokens · 22813 ms · 2026-06-26T08:06:26.318333+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

70 extracted references · 54 canonical work pages · 3 internal anchors

  1. [1]

    Vittorio Gorini, Andrzej Kossakowski, and E. C. G. Sudarshan. Completely positive dynamical semigroups of n-level systems.Journal of Mathematical Physics, 17(5):821–825, 1976.doi: 10.1063/1.522979

    work page doi:10.1063/1.522979 1976

  2. [2]

    Wahrscheinlichkeitstheoretischer Aufbau Der Quantenmechanik

    Goran Lindblad. On the generators of quantum dynamical semigroups.Communications in Mathematical Physics, 48(2):119–130, 1976.doi:10.1007/BF01608499

    work page doi:10.1007/bf01608499 1976

  3. [3]

    Jens Eisert, Dominik Hangleiter, Nathan Walk, Ingo Roth, Damian Markham, Rieffel Keller, and Fernando G. S. L. Brandao. Quantum certification and benchmarking.Nature Reviews Physics, 2(7):382–390, 2020.doi:10.1038/s42254-020-0186-4. 48

    work page doi:10.1038/s42254-020-0186-4 2020

  4. [4]

    Eyal Bairey, Itai Arad, and Netanel H. Lindner. Learning a local hamiltonian from local meas- urements.Physical Review Letters, 122(2), 2019.doi:10.1103/physrevlett.122.020504

    work page doi:10.1103/physrevlett.122.020504 2019

  5. [5]

    Hybrid quantum-classical algo- rithms and quantum error mitigation,

    Suguru Endo, Zhenyu Cai, Simon C. Benjamin, and Xiao Yuan. Hybrid quantum-classical al- gorithms and quantum error mitigation.Journal of the Physical Society of Japan, 90(3):032001, 2021.doi:10.7566/JPSJ.90.032001

    work page doi:10.7566/jpsj.90.032001 2021

  6. [6]

    Wolf, and J

    Frank Verstraete, Michael M. Wolf, and J. Ignacio Cirac. Quantum computation and quantum- state engineering driven by dissipation.Nature Physics, 5(9):633–636, 2009.doi:10.1038/ nphys1342

    2009

  7. [7]

    Nielsen and Isaac L

    Michael A. Nielsen and Isaac L. Chuang.Quantum Computation and Quantum Inform- ation: 10th Anniversary Edition. Cambridge University Press, 2012.doi:10.1017/ cbo9780511976667

    2012

  8. [8]

    Prescription for experimental determination of the dynamics of a quantum black box

    Isaac L. Chuang and Michael A. Nielsen. Prescription for experimental determination of the dynamics of a quantum black box.Journal of Modern Optics, 44(11-12):2455–2467, 1997. doi:10.1080/09500349708231894

    work page doi:10.1080/09500349708231894 1997

  9. [9]

    J. F. Poyatos, J. I. Cirac, and P. Zoller. Complete characterization of a quantum process: The two-bit quantum gate.Physical Review Letters, 78(2), 1997.doi:10.1103/physrevlett.78. 390

    work page doi:10.1103/physrevlett.78 1997

  10. [10]

    Parts and Wholes: Implicative Patterns in Inflectional Paradigms

    Heinz-Peter Breuer and Francesco Petruccione.The Theory of Open Quantum Systems. Oxford University PressOxford, 2007.doi:10.1093/acprof:oso/9780199213900.001.0001

    work page doi:10.1093/acprof:oso/9780199213900.001.0001 2007

  11. [11]

    Near-optimal deterministic network decomposition and ruling set, and improved MIS

    Ainesh Bakshi, Allen Liu, Ankur Moitra, and Ewin Tang. Structure learning of hamiltonians from real-time evolution. InProceedings of the 65th IEEE Annual Symposium on Foundations of Computer Science, pages 1037–1050. IEEE, 2024.doi:10.1109/focs61266.2024.00069

    work page doi:10.1109/focs61266.2024.00069 2024

  12. [12]

    Markovich, V

    Daniel Stilck Fran¸ ca, Liubov A. Markovich, V. V. Dobrovitski, Albert H. Werner, and Jo- hannes Borregaard. Efficient and robust estimation of many-qubit Hamiltonians.Nature Communications, 15(1), 2024.doi:10.1038/s41467-023-44012-5

    work page doi:10.1038/s41467-023-44012-5 2024

  13. [13]

    Learning many-body hamiltonians with heisenberg-limited scaling.Physical Review Letters, 130(20), 2023.doi:10.1103/ physrevlett.130.200403

    Hsin-Yuan Huang, Yu Tong, Di Fang, and Yuan Su. Learning many-body hamiltonians with heisenberg-limited scaling.Physical Review Letters, 130(20), 2023.doi:10.1103/ physrevlett.130.200403

    2023

  14. [14]

    Lindner, and Eyal Bairey

    Assaf Zubida, Elad Yitzhaki, Netanel H. Lindner, and Eyal Bairey. Optimal short-time meas- urements for hamiltonian learning, 2021.doi:10.48550/ARXIV.2108.08824

    work page doi:10.48550/arxiv.2108.08824 2021

  15. [15]

    Matthias C. Caro. Learning quantum processes and hamiltonians via the pauli transfer matrix. ACM Transactions on Quantum Computing, 5(2):1–53, 2024.doi:10.1145/3670418

    work page doi:10.1145/3670418 2024

  16. [16]

    Quantum model learning agent: characterisation of quantum systems through machine learn- ing.New Journal of Physics, 24(5), 2022.doi:10.1088/1367-2630/ac68ff

    Brian Flynn, Antonio A Gentile, Nathan Wiebe, Raffaele Santagati, and Anthony Laing. Quantum model learning agent: characterisation of quantum systems through machine learn- ing.New Journal of Physics, 24(5), 2022.doi:10.1088/1367-2630/ac68ff

    work page doi:10.1088/1367-2630/ac68ff 2022

  17. [17]

    Andi Gu, Lukasz Cincio, and Patrick J. Coles. Practical hamiltonian learning with unit- ary dynamics and gibbs states.Nature Communications, 15(1), 2024.doi:10.1038/ s41467-023-44008-1. 49

    2024

  18. [18]

    Holz¨ apfel, T

    M. Holz¨ apfel, T. Baumgratz, M. Cramer, and M. B. Plenio. Scalable reconstruction of unitary processes and hamiltonians.Physical Review A, 91(4), 2015.doi:10.1103/physreva.91. 042129

    work page doi:10.1103/physreva.91 2015

  19. [19]

    Caro, Albert H

    Tim M¨ obus, Andreas Bluhm, Matthias C. Caro, Albert H. Werner, and Cambyse Rouz´ e. Dissipation-enabled bosonic Hamiltonian learning via new information-propagation bounds, 2023.doi:10.48550/ARXIV.2307.15026

    work page doi:10.48550/arxiv.2307.15026 2023

  20. [20]

    Heisenberg-limited hamiltonian learning for interacting bosons.npj Quantum Information, 10(1), 2024.doi: 10.1038/s41534-024-00881-2

    Haoya Li, Yu Tong, Tuvia Gefen, Hongkang Ni, and Lexing Ying. Heisenberg-limited hamiltonian learning for interacting bosons.npj Quantum Information, 10(1), 2024.doi: 10.1038/s41534-024-00881-2

    work page doi:10.1038/s41534-024-00881-2 2024

  21. [21]

    Werner, and Cambyse Rouz´ e

    Tim M¨ obus, Andreas Bluhm, Tuvia Gefen, Yu Tong, Albert H. Werner, and Cambyse Rouz´ e. Heisenberg-limited hamiltonian learning continuous variable systems via engineered dissipa- tion, 2025.doi:10.48550/ARXIV.2506.00606

    work page doi:10.48550/arxiv.2506.00606 2025

  22. [22]

    da Silva, Olivier Landon-Cardinal, and David Poulin

    Marcus P. da Silva, Olivier Landon-Cardinal, and David Poulin. Practical characterization of quantum devices without tomography.Physical Review Letters, 107(21), 2011.doi:10.1103/ physrevlett.107.210404

    2011

  23. [23]

    Nathan Wiebe, Christopher Granade, Christopher Ferrie, and D. G. Cory. Hamiltonian learning and certification using quantum resources.Physical Review Letters, 112(19), 2014. doi:10.1103/physrevlett.112.190501

    work page doi:10.1103/physrevlett.112.190501 2014

  24. [24]

    Daniel Stilck Fran¸ ca, Tim M¨ obus, Cambyse Rouz´ e, and Albert H. Werner. Learning and certification of local time-dependent quantum dynamics and noise, 2025.doi:10.48550/ ARXIV.2510.08500

    arXiv 2025

  25. [25]

    Petr Ivashkov, Nikita Romanov, Weiyuan Gong, Andi Gu, Hong-Ye Hu, and Susanne F. Yelin. Ansatz-free learning of lindbladian dynamics in situ, 2026.doi:10.48550/ARXIV.2603.05492

    work page doi:10.48550/arxiv.2603.05492 2026

  26. [26]

    Lindbladian learning with neural differential equations, 2026.doi: 10.48550/ARXIV.2603.07778

    Timothy Heightman, Roman Aseguinolaza Gallo, Edward Jiang, JRM Saavedra, Antonio Ac´ ın, and Marcin P lodzie´ n. Lindbladian learning with neural differential equations, 2026.doi: 10.48550/ARXIV.2603.07778

    work page doi:10.48550/arxiv.2603.07778 2026

  27. [27]

    Lieb and Derek W

    Elliott H. Lieb and Derek W. Robinson. The finite group velocity of quantum spin systems. Communications in Mathematical Physics, 28(3):251–257, 1972.doi:10.1007/BF01645779

    work page doi:10.1007/bf01645779 1972

  28. [28]

    Zur fermischen theorie des ?-zerfalls.Zeitschrift f¨ ur Physik, 104(7-8), 1937

    Markus Fierz. Zur fermischen theorie des ?-zerfalls.Zeitschrift f¨ ur Physik, 104(7-8), 1937. doi:10.1007/bf01330070

    work page doi:10.1007/bf01330070 1937

  29. [29]

    Lieb-robinson bounds and the exponential clustering theorem.Communications in Mathematical Physics, 265(1):119–130, 2006.doi:10.1007/ s00220-006-1556-1

    Bruno Nachtergaele and Robert Sims. Lieb-robinson bounds and the exponential clustering theorem.Communications in Mathematical Physics, 265(1):119–130, 2006.doi:10.1007/ s00220-006-1556-1

    2006

  30. [30]

    Hastings

    Matthew B. Hastings. An area law for one-dimensional quantum systems.Journal of Statistical Mechanics: Theory and Experiment, 2007(08):P08024, 2007.doi:10.1088/1742-5468/2007/ 08/p08024

    work page doi:10.1088/1742-5468/2007/ 2007

  31. [31]

    Lower Bounds for Learning Hamiltonians from Time Evolution

    Ziyun Chen, Jerry Li, and Joseph Slote. Lower bounds for learning hamiltonians from time evolution, 2025.doi:10.48550/ARXIV.2509.20665. 50

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2509.20665 2025

  32. [32]

    Projected least- squares quantum process tomography.Quantum, 6, 2022.doi:10.22331/q-2022-10-20-844

    Trystan Surawy-Stepney, Jonas Kahn, Richard Kueng, and Madalin Guta. Projected least- squares quantum process tomography.Quantum, 6, 2022.doi:10.22331/q-2022-10-20-844

    work page doi:10.22331/q-2022-10-20-844 2022

  33. [33]

    Predicting many properties of a quantum system from very few measurements.Nature Physics, 16(10), 2020.doi:10.1038/ s41567-020-0932-7

    Hsin-Yuan Huang, Richard Kueng, and John Preskill. Predicting many properties of a quantum system from very few measurements.Nature Physics, 16(10), 2020.doi:10.1038/ s41567-020-0932-7

    2020

  34. [34]

    Physical Review A89, 023619 (2014) https://doi.org/10.1103/PhysRevA

    Jonathan Kunjummen, Minh C. Tran, Daniel Carney, and Jacob M. Taylor. Shadow process tomography of quantum channels.Physical Review A, 107(4), 2023.doi:10.1103/physreva. 107.042403

    work page doi:10.1103/physreva 2023

  35. [35]

    Tristan Kraft, Manoj K. Joshi, William Lam, Tobias Olsacher, Florian Kranzl, Johannes Franke, Lata Kh Joshi, Rainer Blatt, Augusto Smerzi, Daniel Stilck Fran¸ ca, Benoˆ ıt Vermersch, Barbara Kraus, Christian F. Roos, and Peter Zoller. Bounded-error quantum simulation via hamiltonian and lindbladian learning, 2025.doi:10.48550/ARXIV.2511.23392

    work page doi:10.48550/arxiv.2511.23392 2025

  36. [36]

    Learning quantum hamiltonians from high- temperature gibbs states and real-time evolutions.Nature Physics, 20(6), 2024.doi:10.1038/ s41567-023-02376-x

    Jeongwan Haah, Robin Kothari, and Ewin Tang. Learning quantum hamiltonians from high- temperature gibbs states and real-time evolutions.Nature Physics, 20(6), 2024.doi:10.1038/ s41567-023-02376-x

    2024

  37. [37]

    O’Brien, and Thomas Schuster

    Alicja Dutkiewicz, Thomas E. O’Brien, and Thomas Schuster. The advantage of quantum control in many-body hamiltonian learning.Quantum, 8, 2024.doi:10.22331/ q-2024-11-26-1537

    2024

  38. [38]

    Flammia, and Susanne F

    Hong-Ye Hu, Muzhou Ma, Weiyuan Gong, Qi Ye, Yu Tong, Steven T. Flammia, and Susanne F. Yelin. Ansatz-free hamiltonian learning with heisenberg-limited scaling.PRX Quantum, 6(4), 2025.doi:10.1103/j7b8-pb77

    work page doi:10.1103/j7b8-pb77 2025

  39. [39]

    Learning the structure of any hamiltonian from minimal assumptions

    Andrew Zhao. Learning the structure of any hamiltonian from minimal assumptions. In Proceedings of the 57th Annual ACM Symposium on Theory of Computing, STOC ’25. ACM, 2025.doi:10.1145/3717823.3718115

    work page doi:10.1145/3717823.3718115 2025

  40. [40]

    Learning the dynamics of open quantum systems from their steady states.New Journal of Physics, 22(3), 2020

    Eyal Bairey, Chu Guo, Dario Poletti, Netanel H Lindner, and Itai Arad. Learning the dynamics of open quantum systems from their steady states.New Journal of Physics, 22(3), 2020. doi:10.1088/1367-2630/ab73cd

    work page doi:10.1088/1367-2630/ab73cd 2020

  41. [41]

    Sample-efficient learning of interacting quantum systems.Nature Physics, 17(8), 2021

    Anurag Anshu, Srinivasan Arunachalam, Tomotaka Kuwahara, and Mehdi Soleimanifar. Sample-efficient learning of interacting quantum systems.Nature Physics, 17(8), 2021. doi:10.1038/s41567-021-01232-0

    work page doi:10.1038/s41567-021-01232-0 2021

  42. [42]

    Learning quantum hamiltonians at any temperature in polynomial time

    Ainesh Bakshi, Allen Liu, Ankur Moitra, and Ewin Tang. Learning quantum hamiltonians at any temperature in polynomial time. InProceedings of the 56th Annual ACM Symposium on Theory of Computing, STOC ’24. ACM, 2024.doi:10.1145/3618260.3649619

    work page doi:10.1145/3618260.3649619 2024

  43. [43]

    Chi-Fang Chen, Anurag Anshu, and Quynh T. Nguyen. Learning quantum gibbs states locally and efficiently. In2025 IEEE 66th Annual Symposium on Foundations of Computer Science (FOCS). IEEE, 2025.doi:10.1109/focs63196.2025.00076

    work page doi:10.1109/focs63196.2025.00076 2025

  44. [44]

    Efficient hamiltonian learning from gibbs states, 2024.doi:10.48550/ ARXIV.2403.18061

    Adam Artymowicz. Efficient hamiltonian learning from gibbs states, 2024.doi:10.48550/ ARXIV.2403.18061. 51

    arXiv 2024

  45. [45]

    Characterization and verification of trotterized digital quantum simulation via hamiltonian and liouvillian learning

    Lorenzo Pastori, Tobias Olsacher, Christian Kokail, and Peter Zoller. Characterization and verification of trotterized digital quantum simulation via hamiltonian and liouvillian learning. PRX Quantum, 3(3), 2022.doi:10.1103/prxquantum.3.030324

    work page doi:10.1103/prxquantum.3.030324 2022

  46. [46]

    Large-scale lindblad learning from time-series data, 2025.doi:10.48550/ARXIV.2512.08165

    Ewout van den Berg, Brad Mitchell, Ken Xuan Wei, and Moein Malekakhlagh. Large-scale lindblad learning from time-series data, 2025.doi:10.48550/ARXIV.2512.08165

    work page doi:10.48550/arxiv.2512.08165 2025

  47. [47]

    Hamilto- nian and liouvillian learning in weakly-dissipative quantum many-body systems.Quantum Science and Technology, 10(1), 2025.doi:10.1088/2058-9565/ad9ed5

    Tobias Olsacher, Tristan Kraft, Christian Kokail, Barbara Kraus, and Peter Zoller. Hamilto- nian and liouvillian learning in weakly-dissipative quantum many-body systems.Quantum Science and Technology, 10(1), 2025.doi:10.1088/2058-9565/ad9ed5

    work page doi:10.1088/2058-9565/ad9ed5 2025

  48. [48]

    Rune Thinggaard Birke, Johann Bock Severin, Malthe A. Marciniak, Emil Hogedal, Andreas Nylander, Irshad Ahmad, Amr Osman, Janka Bizn´ arov´ a, Marcus Rommel, Anita Fadavi Roud- sari, Jonas Bylander, Giovanna Tancredi, Daniel Stilck Fran¸ ca, Albert Werner, Christopher W. Warren, Jacob Hastrup, Svend Krøjer, and Morten Kjaergaard. Demonstrating and bench- ...

    work page doi:10.48550/arxiv.2602.14694 2026

  49. [49]

    Reconstruction of Markov random fields from samples: Some observations and algorithms.SIAM Journal on Computing, 42(2):563–578, 2013.doi:10.1137/100796029

    Guy Bresler, Elchanan Mossel, and Allan Sly. Reconstruction of Markov random fields from samples: Some observations and algorithms.SIAM Journal on Computing, 42(2):563–578, 2013.doi:10.1137/100796029

    work page doi:10.1137/100796029 2013

  50. [50]

    Efficiently learning Ising models on arbitrary graphs

    Guy Bresler. Efficiently learning Ising models on arbitrary graphs. InProceedings of the Forty-Seventh Annual ACM Symposium on Theory of Computing, STOC ’15, pages 771–782. Association for Computing Machinery, 2015.doi:10.1145/2746539.2746631

    work page doi:10.1145/2746539.2746631 2015

  51. [51]

    Lokhov, and Michael Chertkov

    Marc Vuffray, Sidhant Misra, Andrey Y. Lokhov, and Michael Chertkov. Interaction screening: Efficient and sample-optimal learning of Ising models. InAdvances in Neural Information Processing Systems, volume 29, pages 2603–2611, 2016

    2016

  52. [52]

    Information theoretic properties of Markov random fields, and their algorithmic applications

    Linus Hamilton, Frederic Koehler, and Ankur Moitra. Information theoretic properties of Markov random fields, and their algorithmic applications. InAdvances in Neural Information Processing Systems, volume 30, pages 2463–2472, 2017

    2017

  53. [53]

    Klivans and Raghu Meka

    Adam R. Klivans and Raghu Meka. Learning graphical models using multiplicative weights. In2017 IEEE 58th Annual Symposium on Foundations of Computer Science, FOCS ’17, pages 343–354. IEEE, 2017.doi:10.1109/FOCS.2017.39

    work page doi:10.1109/focs.2017.39 2017

  54. [54]

    Santhanam and Martin J

    Narayana P. Santhanam and Martin J. Wainwright. Information-theoretic limits of select- ing binary graphical models in high dimensions.IEEE Transactions on Information Theory, 58(7):4117–4134, 2012.doi:10.1109/TIT.2012.2191659

    work page doi:10.1109/tit.2012.2191659 2012

  55. [55]

    Structure learning of antiferromagnetic ising models

    Guy Bresler, David Gamarnik, and Devavrat Shah. Structure learning of antiferromagnetic ising models. In Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K. Weinberger, editors,Advances in Neural Information Processing Systems, volume 27. Curran Associates, Inc., 2014

    2014

  56. [56]

    Proceedings of the 57th Annual ACM Symposium on Theory of Computing , pages =

    Jason Gaitonde, Ankur Moitra, and Elchanan Mossel. Bypassing the noisy parity barrier: Learning higher-order markov random fields from dynamics. InProceedings of the 57th Annual ACM Symposium on Theory of Computing, STOC ’25, page 348–359. ACM, 2025.doi: 10.1145/3717823.3718231. 52

    work page doi:10.1145/3717823.3718231 2025

  57. [57]

    IEEE Transactions on Information Theory , author =

    Guy Bresler, David Gamarnik, and Devavrat Shah. Learning graphical models from the Glauber dynamics.IEEE Transactions on Information Theory, 64(6):4072–4080, 2018. doi:10.1109/TIT.2017.2713828

    work page doi:10.1109/tit.2017.2713828 2018

  58. [58]

    Finite speed of quantum scrambling with long range interactions.Physical Review Letters, 123(25), 2019.doi:10.1103/physrevlett.123.250605

    Chi-Fang Chen and Andrew Lucas. Finite speed of quantum scrambling with long range interactions.Physical Review Letters, 123(25), 2019.doi:10.1103/physrevlett.123.250605

    work page doi:10.1103/physrevlett.123.250605 2019

  59. [59]

    Speed limits and locality in many- body quantum dynamics.Reports on Progress in Physics, 86(11), 2023.doi:10.1088/ 1361-6633/acfaae

    Chi-Fang (Anthony) Chen, Andrew Lucas, and Chao Yin. Speed limits and locality in many- body quantum dynamics.Reports on Progress in Physics, 86(11), 2023.doi:10.1088/ 1361-6633/acfaae

    2023

  60. [60]

    Operator growth bounds from graph theory.Communic- ations in Mathematical Physics, 385(3), 2021.doi:10.1007/s00220-021-04151-6

    Chi-Fang Chen and Andrew Lucas. Operator growth bounds from graph theory.Communic- ations in Mathematical Physics, 385(3), 2021.doi:10.1007/s00220-021-04151-6

    work page doi:10.1007/s00220-021-04151-6 2021

  61. [61]

    Non-perturbative dynamics of the operator size distribution in the sach- dev–ye–kitaev model.Journal of Mathematical Physics, 61(8), 2020.doi:10.1063/1.5133964

    Andrew Lucas. Non-perturbative dynamics of the operator size distribution in the sach- dev–ye–kitaev model.Journal of Mathematical Physics, 61(8), 2020.doi:10.1063/1.5133964

    work page doi:10.1063/1.5133964 2020

  62. [62]

    Operator growth bounds in a cartoon matrix model

    Andrew Lucas and Andrew Osborne. Operator growth bounds in a cartoon matrix model. Journal of Mathematical Physics, 61(12), 2020.doi:10.1063/5.0022177

    work page doi:10.1063/5.0022177 2020

  63. [63]

    Robust polynomial regression up to the in- formation theoretic limit

    Daniel Kane, Sushrut Karmalkar, and Eric Price. Robust polynomial regression up to the in- formation theoretic limit. In2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS). IEEE, 2017.doi:10.1109/focs.2017.43

    work page doi:10.1109/focs.2017.43 2017

  64. [64]

    Arnab Bhattacharyya, Sutanu Gayen, Eric Price, and N. V. Vinodchandran. Near-optimal learning of tree-structured distributions by chow-liu. InProceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing, STOC ’21, page 147–160. ACM, 2021.doi: 10.1145/3406325.3451066

    work page doi:10.1145/3406325.3451066 2021

  65. [65]

    Springer New York, 1997.doi: 10.1007/978-1-4612-1880-7_29

    Bin Yu.Assouad, Fano, and Le Cam, pages 423–435. Springer New York, 1997.doi: 10.1007/978-1-4612-1880-7_29

    work page doi:10.1007/978-1-4612-1880-7_29 1997

  66. [66]

    Nikita Romanov, Petr Ivashkov, Weiyuan Gong, Ishaan Kannan, Andi Gu, Hong-Ye Hu, and Susanne F. Yelin. Learning arbitrary lindbladians with quantum error correction, 2026. doi:10.48550/ARXIV.2606.18188

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2606.18188 2026

  67. [67]

    Near-Optimal Learning of Local Lindbladians

    Itai Arad, Zhili Chen, Naixu Guo, Patrick Rebentrost, and Zhan Yu. Near-optimal learning of local lindbladians, 2026.doi:10.48550/ARXIV.2606.20535

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2606.20535 2026

  68. [68]

    Springer US, 2002.doi:10.1007/ b105286

    Etienne de Klerk.Aspects of Semidefinite Programming. Springer US, 2002.doi:10.1007/ b105286

    2002

  69. [69]

    SIAM Studies in Applied Mathematics

    Yurii Nesterov and Arkadii Nemirovski.Interior-Point Polynomial Algorithms in Convex Pro- gramming. SIAM Studies in Applied Mathematics. Society for Industrial and Applied Math- ematics, Philadelphia, PA, 1994.doi:10.1137/1.9781611970791

    work page doi:10.1137/1.9781611970791 1994

  70. [70]

    Semidefinite programming.SIAM Review, 38(1), 1996.doi:10.1137/1038003

    Lieven Vandenberghe and Stephen Boyd. Semidefinite programming.SIAM Review, 38(1), 1996.doi:10.1137/1038003. 53

    work page doi:10.1137/1038003 1996