Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

IEICE Technical Report; IEICE Tech. Rep.

Sample-efficient Hamiltonian learning of quantum many-body systems

Anurag Anshu, Srinivasan Arunachalam, Tomotaka Kuwahara, Mehdi Soleimanifar

Published Mar 1, 2021• 0 citations
OpenAlex

Related papers

Sample-efficient learning of quantum many-body systems

Anurag Anshu, Srinivasan Arunachalam, Tomotaka Kuwahara +1 more

We study the problem of learning the Hamiltonian of a quantum many-body system given samples from its Gibbs (thermal) state. The classical analog of this problem, known as learning graphical models or Boltzmann machines, is a well-studied question in machine learning and statistics. In this work, we give the first sample-efficient algorithm for the quantum Hamiltonian learning problem. In particular, we prove that polynomially many samples in the number of particles (qudits) are necessary and sufficient for learning the parameters of a spatially local Hamiltonian in l_2-norm. Our main contribution is in establishing the strong convexity of the log-partition function of quantum many-body systems, which along with the maximum entropy estimation yields our sample-efficient algorithm. Classically, the strong convexity for partition functions follows from the Markov property of Gibbs distributions. This is, however, known to be violated in its exact form in the quantum case. We introduce several new ideas to obtain an unconditional result that avoids relying on the Markov property of quantum systems, at the cost of a slightly weaker bound. In particular, we prove a lower bound on the variance of quasi-local operators with respect to the Gibbs state, which might be of independent interest. Our work paves the way toward a more rigorous application of machine learning techniques to quantum many-body problems.

Annual Symposium on Foundations of Computer Science•Nov 1, 2020•10 citations

Sample-efficient learning of interacting quantum systems

Anurag Anshu, Srinivasan Arunachalam, Tomotaka Kuwahara +1 more

arXiv:2004.07266•Nature Physics•May 24, 2021•126 citations

The stationarity test: a framework for learning quantum many-body systems from their thermal states

Thiago Bergamaschi

The task of learning the Hamiltonian interactions governing a quantum system, given samples of its thermal (or 'Gibbs') states, is a foundational question at the intersection of quantum learning theory and many-body physics. In this paper, we draw connections to the quantum Gibbs sampling literature to introduce a natural learning algorithm we call the stationarity test: which simply "guesses" the Hamiltonian, and measures the rate-of-change of local observables, under the associated detailed-balanced quantum Markov chain [CKG23]. We leverage the stationarity test to address the following applications: 1. To give the first learning algorithm for the underlying interaction graph, i.e. structure learning, of lattice Hamiltonians at all temperatures, given copies of their Gibbs states. 2. To give the first learning algorithm for the coefficients of a lattice Hamiltonian, given only copies of its thermal metastable states, modeled as the "local minima" of the free energy. 3. In addition, we present a refinement to the recent area law for thermal metastable states [BCV25], which holds in the thermodynamic limit. Our learning algorithms are rigorous, time-efficient, and nearly sample-optimal in system size and accuracy. At a technical level, our arguments are based on new approximate locality and convexity properties for the quantum Fisher information of these Gibbs sampling algorithms.

quant-pharXiv:2610.01074•Oct 2, 2026•0 citations

Hardware-efficient learning of quantum many-body states

Anonymous

Physical Review Letters•May 22, 2025•1 citation

Efficient Hamiltonian, structure and trace distance learning of Gaussian states

Marco Fanizza, Cambyse Rouzé, Daniel Stilck França

When learning descriptions of many-body quantum systems, assuming locality of interactions can dramatically reduce the required number of observations and computational time compared to unstructured approaches. In this work, we uncover an infinite-dimensional instance of this phenomenon, initiating the study of Hamiltonian learning for positive-temperature bosonic Gaussian states. We present sample- and computationally efficient protocols for inferring the parameters and graph structure of underlying quadratic Hamiltonians, provided that temperature, squeezing, displacement, and the interaction graph's maximal degree are bounded. Notably, our protocol relies solely on heterodyne measurements, which are often experimentally feasible, and achieves a sample complexity that scales only logarithmically with the number of modes. Furthermore, our techniques allow for the learning of positive-temperature Gaussian states in trace distance with quadratic scaling in precision and polynomial scaling in the number of modes.

arXiv:2411.03163•Nature Communications•Sep 16, 2026•0 citations

Experimental quantum Hamiltonian learning

Jianwei Wang, Stefano Paesani, Raffaele Santagati +8 more

arXiv:1703.05402•Nature Physics•Mar 13, 2017•248 citations
We study the problem of learning the Hamiltonian of a quantum many-body system given samples from its Gibbs (thermal) state. The classical analog of this problem, known as learning graphical models or Boltzmann machines, is a well-studied question in machine learning and statistics. In this work, we give the first sample-efficient algorithm for the quantum Hamiltonian learning problem. In particular, we prove that polynomially many samples in the number of particles (qudits) are necessary and sufficient for learning the parameters of a spatially local Hamiltonian in l_2-norm. Our main contribution is in establishing the strong convexity of the log-partition function of quantum many-body systems, which along with the maximum entropy estimation yields our sample-efficient algorithm. Classically, the strong convexity for partition functions follows from the Markov property of Gibbs distributions. This is, however, known to be violated in its exact form in the quantum case. We introduce several new ideas to obtain an unconditional result that avoids relying on the Markov property of quantum systems, at the cost of a slightly weaker bound. In particular, we prove a lower bound on the variance of quasi-local operators with respect to the Gibbs state, which might be of independent interest. Our work paves the way toward a more rigorous application of machine learning techniques to quantum many-body problems.
The task of learning the Hamiltonian interactions governing a quantum system, given samples of its thermal (or 'Gibbs') states, is a foundational question at the intersection of quantum learning theory and many-body physics. In this paper, we draw connections to the quantum Gibbs sampling literature to introduce a natural learning algorithm we call the stationarity test: which simply "guesses" the Hamiltonian, and measures the rate-of-change of local observables, under the associated detailed-balanced quantum Markov chain [CKG23]. We leverage the stationarity test to address the following applications: 1. To give the first learning algorithm for the underlying interaction graph, i.e. structure learning, of lattice Hamiltonians at all temperatures, given copies of their Gibbs states. 2. To give the first learning algorithm for the coefficients of a lattice Hamiltonian, given only copies of its thermal metastable states, modeled as the "local minima" of the free energy. 3. In addition, we present a refinement to the recent area law for thermal metastable states [BCV25], which holds in the thermodynamic limit. Our learning algorithms are rigorous, time-efficient, and nearly sample-optimal in system size and accuracy. At a technical level, our arguments are based on new approximate locality and convexity properties for the quantum Fisher information of these Gibbs sampling algorithms.
When learning descriptions of many-body quantum systems, assuming locality of interactions can dramatically reduce the required number of observations and computational time compared to unstructured approaches. In this work, we uncover an infinite-dimensional instance of this phenomenon, initiating the study of Hamiltonian learning for positive-temperature bosonic Gaussian states. We present sample- and computationally efficient protocols for inferring the parameters and graph structure of underlying quadratic Hamiltonians, provided that temperature, squeezing, displacement, and the interaction graph's maximal degree are bounded. Notably, our protocol relies solely on heterodyne measurements, which are often experimentally feasible, and achieves a sample complexity that scales only logarithmically with the number of modes. Furthermore, our techniques allow for the learning of positive-temperature Gaussian states in trace distance with quadratic scaling in precision and polynomial scaling in the number of modes.