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

arXiv:2609.26705

When are bosonic Gaussian states classical to learn?

Senrui Chen, Antonio Anna Mele, Francesco Anna Mele, John Preskill

quant-phcs.ITcs.LGmath-phSubmitted Sep 22, 2026• Announced Sep 23, 2026• 3 citations
arXivHTMLPDF

Abstract

A fundamental question in physics is: When does classical behavior emerge from quantum systems? Bosonic Gaussian states provide a natural setting to explore this quantum-classical boundary, as they capture both the classical field behavior and the intrinsic quantum nature of light. Here, we address this problem from a learning-theoretic perspective by asking: When are bosonic Gaussian states classical to learn? That is, under what conditions (if any) can an n-mode bosonic Gaussian state be learned with as few samples, and with operations as simple, as are needed to learn a classical 2n-variate Gaussian distribution? We establish a smooth crossover in learnability governed by the state's thermal fluctuations: - Cold Gaussian states are non-classical to learn: When the covariance matrix satisfies $Σ\le(\frac12+O(\frac1n))I$, i.e. close to the vacuum covariance, tomography under single-copy (i.e., non-entangled) measurements fundamentally requires $Ω(n^3)$ copies, strictly exceeding the sample complexity $Θ(n^2)$ of learning classical Gaussian distributions. We show that this hardness persists even when few-copy entangled measurements are allowed. - Warm Gaussian states are classical to learn: When thermal fluctuations exceed the vacuum noise, parameterized by $Σ\ge(\frac12+ν)I$ for any parameter $ν>0$, we prove that single-copy tomography requires $N=Θ\left(n^2\min(n,1+ν^{-1})\right)$ copies. This bound is tight and is achieved by simple, non-adaptive, unentangled heterodyne measurements. Crucially, for $ν=Ω(1)$, the sample complexity drops to $Θ(n^2)$, matching the classical case. Our results tightly characterize a quantum-to-classical crossover in the learnability of bosonic Gaussian states, reveal a novel connection between fundamental physics and statistical learning theory, and have implications for real-world sensing experiments.

AI Summary

The paper asks when tomography of an $n$-mode bosonic Gaussian state matches learning a classical $2n$-variate Gaussian distribution in sample complexity while using only single-copy measurements. Accuracy is measured in trace distance, with constant success probability; the classical benchmark is $\Theta(n^2/\varepsilon^2)$ samples. For general Gaussian states, any possibly adaptive single-copy protocol requires $\Omega(n^3/\varepsilon^2)$ copies. Hard instances can be passive states satisfying $\Sigma\preceq(1/2+O(1/n))I$, with constant total expected photon number. Measurements on at most $k$ fresh copies, without quantum memory between blocks, require $\Omega(n^3/[\varepsilon^2\min\{\sqrt{k},n\}])$ copies. Under the promise $\Sigma\succeq(1/2+\nu)I$, the single-copy complexity is exactly $\Theta((n^2/\varepsilon^2)\min\{n,1+\nu^{-1}\})$, achieved by nonadaptive heterodyne measurements. Thus the cubic scaling persists for $\nu\lesssim1/n$, crosses through $\Theta(n^2/(\nu\varepsilon^2))$, and becomes quadratic for $\nu=\Omega(1)$. The cold-state bounds use a reduction encoding finite-dimensional mixed states into low-energy passive Gaussian states. Temperature-dependent lower bounds extend Bayesian posterior anti-concentration to bosonic photon-number sectors using symmetric-power representations and Schur polynomials. The upper bound combines empirical heterodyne statistics, covariance inflation to ensure physicality, and a one-sided covariance-to-trace-distance bound. The results concern worst-case full tomography, not structured sensing or estimation of selected properties; the experimental comparisons do not establish corresponding sensing bounds. The $k$-copy lower bound lacks a matching upper bound. The crossover promise bounds ordinary covariance eigenvalues and does not cover squeezed states with quadrature variance below vacuum.

Little sign of AI-generated textAI use disclosed
GPT-5.6 Sol and GPT-6 were used to strengthen several of our technical results, and to help check the mathematical arguments and improve the exposition.

Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.

Comments
comments welcome

Related papers

What resources are needed for optimal learning of bosonic Gaussian states?

Senrui Chen, Francesco Anna Mele, Marco Fanizza +5 more

Continuous-variable systems enable key quantum technologies in computation, communication, and sensing. Bosonic Gaussian states emerge naturally in various such applications, including gravitational-wave and dark-matter detection. A fundamental question is how to characterize an unknown bosonic Gaussian state from as few samples as possible. Despite decades-long exploration, the ultimate efficiency limit remains unclear. In this work, we study the necessary and sufficient number of copies to learn an $n$-mode Gaussian state, with energy less than $E$, to $\varepsilon$ trace distance with high probability. We prove a lower bound of $Ω(n^3/\varepsilon^2)$ for Gaussian measurements, matching the best known upper bound up to doubly-log energy dependence, and $Ω(n^2/\varepsilon^2)$ for arbitrary measurements. We further show an upper bound of $\widetilde{O}(n^2/\varepsilon^2)$ given that the Gaussian state is promised to be either pure or passive. Interestingly, while Gaussian measurements suffice for nearly optimal learning of pure Gaussian states, non-Gaussian measurements are provably required for optimal learning of passive Gaussian states. Finally, focusing on learning single-mode Gaussian states via non-entangling Gaussian measurements, we provide a nearly tight bound of $\widetildeΘ(E/\varepsilon^2)$ for any non-adaptive schemes, showing adaptivity is indispensable for nearly energy-independent scaling. As a byproduct, we establish sharp bounds on the trace distance between Gaussian states in terms of the total variation distance between their Wigner distributions, and obtain a nearly tight sample complexity bound for learning the Wigner distribution of any Gaussian state to $\varepsilon$ total variation distance. Our results significantly advance quantum learning theory in the bosonic regimes and have practical impact in quantum sensing and benchmarking applications.

quant-pharXiv:2603.18136•Mar 20, 2026•14 citations

When are bosonic Gaussian states classical to learn? — E8 Intelligence Research

Andrew Stewart Caldin

A fundamental question in physics is: When does classical behavior emerge from quantum systems? Bosonic Gaussian states provide a natural setting to explore this quantum-classical boundary, as they capture both the classical field behavior and the intrinsic quantum nature of light. Here, we address this problem from a learning-theoretic perspective by asking: When are bosonic Gaussian states classical to learn? That is, under what conditions (if any) can an n-mode bosonic Gaussian state be learned with as few samples, and with operations as simple, as are needed to learn a classical 2n-variate Gaussian distribution? We establish a smooth crossover in learnability governed by the state's thermal fluctuations: - Cold Gaussian states are non-classical to learn: When the covariance matrix satisfies $Σ\le(\frac12+O(\frac1n))I$, i.e. close to the vacuum covariance, tomography under single-copy (i.e., non-entangled) measurements fundamentally requires $Ω(n^3)$ copies, strictly exceeding the Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com

•Nov 10, 2026•0 citations

The log log jam in Gaussian state tomography

Sitan Chen, Weiyuan Gong, Qi Ye +1 more

Unlike in finite dimensions, quantum information in continuous-variable systems has the peculiar feature that without imposing physical constraints, the sample complexity of state tomography can be unbounded. Remarkably, this is even the case for state-of-the-art protocols for learning Gaussian states, which have finite-dimensional descriptions: the best known rates scale with $\log \log E$, where $E$ is the energy of the system. We prove this is not an artifact of existing analyses, but a fundamental limitation of the measurements used. We show: (1) Any protocol that uses Gaussian measurements, even entangled or adaptively chosen ones, must incur a $\log \log E$ dependence. This answers an open question posed by a number of previous works. (2) There is a smooth tradeoff between the number of rounds of adaptivity and the energy dependence, and we give a matching protocol achieving this interpolated rate. (3) With highly entangled, non-Gaussian measurements, one can learn $n$-mode pure Gaussian states with $O(n^2 / ε^2)$ samples, independent of $E$. This answers an open question posed by Chen et al. (4) A simple protocol based on the single-copy canonical phase POVM of Holevo and Helstrom learns single-mode pure Gaussian states with $O(1/ε^2)$ samples, again independent of $E$. Our results clarify the role of energy in bosonic state tomography and shed new light on the intriguing interplay between adaptivity, entanglement, and magic in quantum learning.

quant-pharXiv:2607.12983•Jul 15, 2026•7 citations

Advances in quantum learning theory with bosonic systems

Francesco Anna Mele

This paper reviews recent advances in quantum learning theory for continuous-variable (CV) systems. Quantum learning theory investigates how to extract classical information from quantum systems as efficiently as possible. CV systems are ubiquitous in nature and in quantum technologies, as they describe bosonic and quantum-optical systems. While quantum learning theory for finite-dimensional systems has been extensively studied, the corresponding theory for CV systems has only recently begun to develop; here we provide a concise review. We focus on the following questions: what is the minimum number of copies (the sample complexity) required to learn a non-Gaussian state, possibly under energy constraints? What is the sample complexity for learning Gaussian states? How does the performance of CV state learning depend on non-Gaussianity? How can one test whether a state is Gaussian or far from the set of Gaussian states? And how can Gaussian processes be learned efficiently? Central to these topics, we also review several bounds on the trace distance between CV states in terms of their covariance matrices, which may be of independent interest. Overall, this work summarises selected developments in tomography of CV systems and highlights a selection of open problems.

quant-pharXiv:2605.08082•May 11, 2026•6 citations

Optimal tomography of bosonic and fermionic Gaussian states

Senrui Chen, Marco Fanizza, Filippo Girardi +4 more

The sample complexity is the minimum number of copies required to learn an accurate classical description of a quantum state. Bosonic and fermionic Gaussian quantum states are families of quantum states that play a key role in quantum science and technology, from quantum optics and many-body physics to quantum chemistry, quantum computing, and quantum information theory. Despite their importance, their sample complexity had not been fully determined. We settle this open problem and show that both bosonic and fermionic Gaussian states can be learned using a number of copies that scales quadratically in the number of modes, regardless of whether the state is pure or mixed, and independently of any energy bound on the state. We derive these results by using the representation theory of Gaussian unitaries and by putting forth a generalization of the random purification channel to this setting and beyond.

quant-pharXiv:2607.11847•Jul 14, 2026•21 citations

Learning Gaussian optical states with quantum computers

Spencer Dimitroff, John Kallaugher, Ashe Miller +1 more

Recent results have established dramatic advantages in learning properties of quantum states when a quantum computer is available to process or jointly measure multiple copies of the unknown quantum state. Learning tasks can be accomplished with exponentially fewer copies of the state when compared to optimized classical learning strategies that are restricted to measuring one copy of the state at a time. While these results were established in abstract settings and for artificial learning tasks, they motivate the application of quantum computers to imaging and sensing of weak electromagnetic fields since these settings are ultimately concerned with the learning of unknown quantum states. In this work we apply these new results in quantum learning to the problem of learning Gaussian states of the electromagnetic field, which are germane since they describe most fields used in imaging and sensing. In order to connect with quantum learning theory, we consider the transduction of an $n$-mode Gaussian state into a register of qubits on a quantum computer followed by optimized measurements on these qubits to extract the parameters defining the original Gaussian state. We rigorously bound the number of copies of the Gaussian state required to achieve worst-case additive error in parameter estimates. The scaling of this bound with $n$ is exponentially better than naïve strategies for characterizing Gaussian states and matches recently derived bounds for characterization of Gaussian states using continuous-variable (CV) classical shadows. In addition, our bound has a polynomially better dependence on the energy of the multimode Gaussian state compared to the CV shadows protocol.

quant-pharXiv:2605.05325•May 8, 2026•3 citations
A fundamental question in physics is: When does classical behavior emerge from quantum systems? Bosonic Gaussian states provide a natural setting to explore this quantum-classical boundary, as they capture both the classical field behavior and the intrinsic quantum nature of light. Here, we address this problem from a learning-theoretic perspective by asking: When are bosonic Gaussian states classical to learn? That is, under what conditions (if any) can an n-mode bosonic Gaussian state be learned with as few samples, and with operations as simple, as are needed to learn a classical 2n-variate Gaussian distribution? We establish a smooth crossover in learnability governed by the state's thermal fluctuations:
  • Cold Gaussian states are non-classical to learn: When the covariance matrix satisfies Σ≤(12+O(1n))IΣ\le(\frac12+O(\frac1n))IΣ≤(21​+O(n1​))I, i.e. close to the vacuum covariance, tomography under single-copy (i.e., non-entangled) measurements fundamentally requires Ω(n3)Ω(n^3)Ω(n3) copies, strictly exceeding the sample complexity Θ(n2)Θ(n^2)Θ(n2) of learning classical Gaussian distributions. We show that this hardness persists even when few-copy entangled measurements are allowed.
  • Warm Gaussian states are classical to learn: When thermal fluctuations exceed the vacuum noise, parameterized by Σ≥(12+ν)IΣ\ge(\frac12+ν)IΣ≥(21​+ν)I for any parameter ν>0ν>0ν>0, we prove that single-copy tomography requires N=Θ(n2min⁡(n,1+ν−1))N=Θ\left(n^2\min(n,1+ν^{-1})\right)N=Θ(n2min(n,1+ν−1)) copies. This bound is tight and is achieved by simple, non-adaptive, unentangled heterodyne measurements. Crucially, for ν=Ω(1)ν=Ω(1)ν=Ω(1), the sample complexity drops to Θ(n2)Θ(n^2)Θ(n2), matching the classical case.
Our results tightly characterize a quantum-to-classical crossover in the learnability of bosonic Gaussian states, reveal a novel connection between fundamental physics and statistical learning theory, and have implications for real-world sensing experiments.
The paper asks when tomography of an nnn-mode bosonic Gaussian state matches learning a classical 2n2n2n-variate Gaussian distribution in sample complexity while using only single-copy measurements. Accuracy is measured in trace distance, with constant success probability; the classical benchmark is Θ(n2/ε2)\Theta(n^2/\varepsilon^2)Θ(n2/ε2) samples.
For general Gaussian states, any possibly adaptive single-copy protocol requires Ω(n3/ε2)\Omega(n^3/\varepsilon^2)Ω(n3/ε2) copies. Hard instances can be passive states satisfying Σ⪯(1/2+O(1/n))I\Sigma\preceq(1/2+O(1/n))IΣ⪯(1/2+O(1/n))I, with constant total expected photon number. Measurements on at most kkk fresh copies, without quantum memory between blocks, require Ω(n3/[ε2min⁡{k,n}])\Omega(n^3/[\varepsilon^2\min\{\sqrt{k},n\}])Ω(n3/[ε2min{k​,n}]) copies. Under the promise Σ⪰(1/2+ν)I\Sigma\succeq(1/2+\nu)IΣ⪰(1/2+ν)I, the single-copy complexity is exactly Θ((n2/ε2)min⁡{n,1+ν−1})\Theta((n^2/\varepsilon^2)\min\{n,1+\nu^{-1}\})Θ((n2/ε2)min{n,1+ν−1}), achieved by nonadaptive heterodyne measurements. Thus the cubic scaling persists for ν≲1/n\nu\lesssim1/nν≲1/n, crosses through Θ(n2/(νε2))\Theta(n^2/(\nu\varepsilon^2))Θ(n2/(νε2)), and becomes quadratic for ν=Ω(1)\nu=\Omega(1)ν=Ω(1).
The cold-state bounds use a reduction encoding finite-dimensional mixed states into low-energy passive Gaussian states. Temperature-dependent lower bounds extend Bayesian posterior anti-concentration to bosonic photon-number sectors using symmetric-power representations and Schur polynomials. The upper bound combines empirical heterodyne statistics, covariance inflation to ensure physicality, and a one-sided covariance-to-trace-distance bound.
The results concern worst-case full tomography, not structured sensing or estimation of selected properties; the experimental comparisons do not establish corresponding sensing bounds. The kkk-copy lower bound lacks a matching upper bound. The crossover promise bounds ordinary covariance eigenvalues and does not cover squeezed states with quadrature variance below vacuum.
Continuous-variable systems enable key quantum technologies in computation, communication, and sensing. Bosonic Gaussian states emerge naturally in various such applications, including gravitational-wave and dark-matter detection. A fundamental question is how to characterize an unknown bosonic Gaussian state from as few samples as possible. Despite decades-long exploration, the ultimate efficiency limit remains unclear. In this work, we study the necessary and sufficient number of copies to learn an nnn-mode Gaussian state, with energy less than EEE, to ε\varepsilonε trace distance with high probability. We prove a lower bound of Ω(n3/ε2)Ω(n^3/\varepsilon^2)Ω(n3/ε2) for Gaussian measurements, matching the best known upper bound up to doubly-log energy dependence, and Ω(n2/ε2)Ω(n^2/\varepsilon^2)Ω(n2/ε2) for arbitrary measurements. We further show an upper bound of O~(n2/ε2)\widetilde{O}(n^2/\varepsilon^2)O(n2/ε2) given that the Gaussian state is promised to be either pure or passive. Interestingly, while Gaussian measurements suffice for nearly optimal learning of pure Gaussian states, non-Gaussian measurements are provably required for optimal learning of passive Gaussian states. Finally, focusing on learning single-mode Gaussian states via non-entangling Gaussian measurements, we provide a nearly tight bound of Θ~(E/ε2)\widetildeΘ(E/\varepsilon^2)Θ(E/ε2) for any non-adaptive schemes, showing adaptivity is indispensable for nearly energy-independent scaling. As a byproduct, we establish sharp bounds on the trace distance between Gaussian states in terms of the total variation distance between their Wigner distributions, and obtain a nearly tight sample complexity bound for learning the Wigner distribution of any Gaussian state to ε\varepsilonε total variation distance. Our results significantly advance quantum learning theory in the bosonic regimes and have practical impact in quantum sensing and benchmarking applications.
A fundamental question in physics is: When does classical behavior emerge from quantum systems? Bosonic Gaussian states provide a natural setting to explore this quantum-classical boundary, as they capture both the classical field behavior and the intrinsic quantum nature of light. Here, we address this problem from a learning-theoretic perspective by asking: When are bosonic Gaussian states classical to learn? That is, under what conditions (if any) can an n-mode bosonic Gaussian state be learned with as few samples, and with operations as simple, as are needed to learn a classical 2n-variate Gaussian distribution? We establish a smooth crossover in learnability governed by the state's thermal fluctuations: - Cold Gaussian states are non-classical to learn: When the covariance matrix satisfies Σ≤(12+O(1n))IΣ\le(\frac12+O(\frac1n))IΣ≤(21​+O(n1​))I, i.e. close to the vacuum covariance, tomography under single-copy (i.e., non-entangled) measurements fundamentally requires Ω(n3)Ω(n^3)Ω(n3) copies, strictly exceeding the Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com
Unlike in finite dimensions, quantum information in continuous-variable systems has the peculiar feature that without imposing physical constraints, the sample complexity of state tomography can be unbounded. Remarkably, this is even the case for state-of-the-art protocols for learning Gaussian states, which have finite-dimensional descriptions: the best known rates scale with log⁡log⁡E\log \log EloglogE, where EEE is the energy of the system. We prove this is not an artifact of existing analyses, but a fundamental limitation of the measurements used. We show: (1) Any protocol that uses Gaussian measurements, even entangled or adaptively chosen ones, must incur a log⁡log⁡E\log \log EloglogE dependence. This answers an open question posed by a number of previous works. (2) There is a smooth tradeoff between the number of rounds of adaptivity and the energy dependence, and we give a matching protocol achieving this interpolated rate. (3) With highly entangled, non-Gaussian measurements, one can learn nnn-mode pure Gaussian states with O(n2/ε2)O(n^2 / ε^2)O(n2/ε2) samples, independent of EEE. This answers an open question posed by Chen et al. (4) A simple protocol based on the single-copy canonical phase POVM of Holevo and Helstrom learns single-mode pure Gaussian states with O(1/ε2)O(1/ε^2)O(1/ε2) samples, again independent of EEE. Our results clarify the role of energy in bosonic state tomography and shed new light on the intriguing interplay between adaptivity, entanglement, and magic in quantum learning.
This paper reviews recent advances in quantum learning theory for continuous-variable (CV) systems. Quantum learning theory investigates how to extract classical information from quantum systems as efficiently as possible. CV systems are ubiquitous in nature and in quantum technologies, as they describe bosonic and quantum-optical systems. While quantum learning theory for finite-dimensional systems has been extensively studied, the corresponding theory for CV systems has only recently begun to develop; here we provide a concise review. We focus on the following questions: what is the minimum number of copies (the sample complexity) required to learn a non-Gaussian state, possibly under energy constraints? What is the sample complexity for learning Gaussian states? How does the performance of CV state learning depend on non-Gaussianity? How can one test whether a state is Gaussian or far from the set of Gaussian states? And how can Gaussian processes be learned efficiently? Central to these topics, we also review several bounds on the trace distance between CV states in terms of their covariance matrices, which may be of independent interest. Overall, this work summarises selected developments in tomography of CV systems and highlights a selection of open problems.
The sample complexity is the minimum number of copies required to learn an accurate classical description of a quantum state. Bosonic and fermionic Gaussian quantum states are families of quantum states that play a key role in quantum science and technology, from quantum optics and many-body physics to quantum chemistry, quantum computing, and quantum information theory. Despite their importance, their sample complexity had not been fully determined. We settle this open problem and show that both bosonic and fermionic Gaussian states can be learned using a number of copies that scales quadratically in the number of modes, regardless of whether the state is pure or mixed, and independently of any energy bound on the state. We derive these results by using the representation theory of Gaussian unitaries and by putting forth a generalization of the random purification channel to this setting and beyond.
Recent results have established dramatic advantages in learning properties of quantum states when a quantum computer is available to process or jointly measure multiple copies of the unknown quantum state. Learning tasks can be accomplished with exponentially fewer copies of the state when compared to optimized classical learning strategies that are restricted to measuring one copy of the state at a time. While these results were established in abstract settings and for artificial learning tasks, they motivate the application of quantum computers to imaging and sensing of weak electromagnetic fields since these settings are ultimately concerned with the learning of unknown quantum states. In this work we apply these new results in quantum learning to the problem of learning Gaussian states of the electromagnetic field, which are germane since they describe most fields used in imaging and sensing. In order to connect with quantum learning theory, we consider the transduction of an nnn-mode Gaussian state into a register of qubits on a quantum computer followed by optimized measurements on these qubits to extract the parameters defining the original Gaussian state. We rigorously bound the number of copies of the Gaussian state required to achieve worst-case additive error in parameter estimates. The scaling of this bound with nnn is exponentially better than naïve strategies for characterizing Gaussian states and matches recently derived bounds for characterization of Gaussian states using continuous-variable (CV) classical shadows. In addition, our bound has a polynomially better dependence on the energy of the multimode Gaussian state compared to the CV shadows protocol.