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:2610.00157

Symmetry Discovery in Quantum Learning: Observable-Level and Task-Level Inference from Finite Measurements

Zeyu Chen

quant-phcs.LGSubmitted Sep 11, 2026• Announced Sep 14, 2026• 0 citations
arXivHTMLPDF

Abstract

Symmetry reduces the capacity of a quantum learning model, but the imposed group must match both the measured information and the label transformation. We establish a finite-measurement theory for inferring this group from candidate transformations. The central structural result identifies observable-invisible transformations with the stabilizer of a projected state whenever the probe span is invariant. It turns recovered generators into a valid subgroup and identifies the continuous invisible space with its Lie algebra. For finite dictionaries, an unbiased shadow statistic distinguishes zero from positive squared expectation discrepancies with an inverse-gap measurement rate, improving the inverse-square-gap rate of uniform discrepancy estimation. A commuting qubit lower bound proves the gap dependence optimal at fixed snapshot scale, and simultaneous intervals support data-dependent tolerances. Task validation then tests either the joint distribution through a characteristic kernel or its encoded mean through a classical--quantum discrepancy. An exact group-average identity relates the latter to joint-state asymmetry and specifies its conversion to binary task breaking mass. Projection bias quantifies the cost of excessive symmetry, while an $\ell_1$ readout bound quantifies the capacity gained by relaxing it. At an invariant pure-state backbone, retained and nontrivial breaking sectors are Fisher-orthogonal. Ising-chain calculations connect finite-shot recovery, label-dependent symmetry, and physical sector drift. These results determine which symmetry the measurements support and provide the statistical and geometric basis for a subsequent release decision.

Related papers

Statistical Symmetry Release for Equivariant Quantum Learning

Zeyu Chen

Hard symmetry constraints reduce model complexity, but can also erase label information. Statistical symmetry release determines when finite data and quantum measurements justify relaxing such a constraint, which directions to open, and how far to move. We connect global signal detection to local, loss-dependent improvement. A two-copy twirl--swap gate estimates task information in the symmetry-breaking complement with a dimension-independent copy count under paired-state and group-unitary access; reweighting the same records resolves representation sectors. An exact duality distinguishes this Hilbert--Schmidt signal from the larger signal accessible to bounded-outcome readouts. Local improvement is governed by the release gradient and a loss-corrected double-commutator matrix. Simultaneous confidence bounds convert empirical direction selection into certified descent, using either shared Pauli measurements or scalar probes with state-independent truncation bounds. Gaussian testing lower bounds quantify the cost of searching over unknown directions in the calibrated local experiment. Independent validation controls adaptively generated models, and a fast squared-loss bound preserves the approximation--estimation rate of a nested release path. On an eight-qubit Ising model, shared measurements certify release with 6300 times fewer shots than the specified scalar estimator on the tested budget grids. Quotient quantum natural gradient then controls parameter redundancy during training. Together, these results turn symmetry relaxation into a statistically justified model-selection decision.

cs.LOCross-listedarXiv:2609.11470•Sep 11, 2026•0 citations

Blind Symmetry Matching in Quantum States with Application to Shot-Count Reduction

Mitchell A. Thornton

Measuring a quantum computation in a basis adapted to a symmetry it carries reduces the repeated measurements, commonly referred to as ``shots'', needed to read a statistical answer. Detecting the symmetry a quantum state carries has many uses: certifying a claimed symmetry, identifying a conserved-charge sector, flagging symmetry-breaking as an error signature, and selecting a compression or readout basis; shot-count reduction is developed here as one exemplary case. Existing methods assume the symmetry is known in advance; we remove that assumption. When it is unknown, the carried symmetry is discovered from the data by a symmetry test that scores candidate groups, and the largest passing group is exploited as the measurement basis. We state the pipeline precisely, prove the selection rule is unbiased, and charge discovery in full. Two conditions are treated, both detected by the same score with a different projection: a weak condition, commutation with the representation, and a strong condition, confinement to a single charge sector, the distinction drawn in the quantum-reference-frame literature. A single circuit, a controlled twirl followed by a SWAP test, discovers both: discarding the group register tests the weak condition, post-selecting it the strong one. The framework is general over finite groups, with cyclic (Fourier), dihedral, and symmetric-group (Schur-Weyl) examples; strong confinement to the symmetric, or Dicke, subspace is an exponential reduction. Seeded demonstrations show the loop wins net of discovery: weak matching on momentum readout reduces shots by a factor widening from ten to several thousand, and strong matching on a two-system target by a further factor of the subsystem size. Blind symmetry matching is a practical primitive for the common case where the matched basis cannot be written down in advance.

quant-pharXiv:2606.19196•Jun 18, 2026•0 citations

Sample Complexity for Generative Learning of Quantum Measurement Data

Shuhan Zhang, Yi-Zhuang You

Generative learning of a quantum measurement distribution from finite data requires choosing a model capacity that balances representation accuracy against estimation cost. We develop a bias-variance framework that decomposes the expected population Kullback-Leibler error at model capacity $s$ and sample size $N$ as $E(s,N)=B(s)+V(s,N)$, with representation bias $B$ and a variance term $V$ capturing the mean estimation error. In the well-sampled regime, $V(s,N)\simeq[NC(s)]^{-1}$, and exponential or algebraic laws for $B$ and $C$ yield four scaling templates for the optimal error, from inverse powers of $N$ to inverse powers of $\ln N$. For local autoregressive models, the context radius sets the model capacity, and $B$ is the summed conditional mutual information lost by truncating the context. For a smoothed histogram learner, we derive an exact finite-sample estimation cost that accounts for rarely observed contexts and recovers the parameter-count law in the well-sampled regime. For transverse-field Ising Born distributions, the independently evaluated bias and estimation cost predict both the optimal context radius and the optimal error. In the well-sampled regime, the estimation cost grows exponentially with context radius. Its competition with approximately exponential bias decay in the gapped regimes predicts power-law error decay in $N$, while algebraic bias decay at criticality predicts asymptotic inverse-power decay in $\ln N$. Bulk-site results are consistent with the corresponding finite-sample predictions. These results connect the structure of quantum measurement distributions to the model capacity justified by finite data.

quant-pharXiv:2610.38028•Oct 29, 2026•0 citations

Group-Invariant Quantum Machine Learning

Martín Larocca, Frédéric Sauvage, Faris M. Sbahi +3 more

Quantum machine learning (QML) models are aimed at learning from data encoded in quantum states.Recently, it has been shown that models with little to no inductive biases (i.e., with no assumptions about the problem embedded in the model) are likely to have trainability and generalization issues, especially for large problem sizes.As such, it is fundamental to develop schemes that encode as much information as available about the problem at hand.In this work we present a simple, yet powerful, framework where the underlying invariances in the data are used to build QML models that, by construction, respect those symmetries.These so-called group-invariant models produce outputs that remain invariant under the action of any element of the symmetry group G associated with the dataset.We present theoretical results underpinning the design of G-invariant models, and exemplify their application through several paradigmatic QML classification tasks, including cases when G is a continuous Lie group and also when it is a discrete symmetry group.Notably, our framework allows us to recover, in an elegant way, several well-known algorithms for the literature, as well as to discover new ones.Taken together, we expect that our results will help pave the way towards a more geometric and group-theoretic approach to QML model design.

arXiv:2205.02261•PRX Quantum•Sep 19, 2022•182 citations

Certification Resources and the Value of Retained Quantum-Reader Records

Jeremy Rodgers

This paper develops task-relative reader certification within Shadow Theory’s source–readout programme. It asks how many source copies are needed to validate a fixed quantum reader, and when access to its retained measurement records reduces that cost compared with observing only its final correct-or-incorrect decisions. The reader is fixed before validation and must return a sign after each complete experiment. A trusted evaluator knows the preparation label for scoring, while the reader does not. The analysis distinguishes terminal-error observations, records with trusted ancillary information, and readable measurement trajectories governed by a shared physical response model. For terminal-error validation, the paper establishes exact finite-budget tests and sequential likelihood tests, together with nearly matching information-theoretic lower bounds on expected source consumption. An unrestricted-record result shows why additional archived data alone need not improve certification: an advantage requires specified information or response constraints. A separate trusted-seed construction gives an exact information-projection test. The central quantitative comparison concerns a fixed fourteen-copy reader in a trusted shared-visibility family. To certify a maximum label error of one percent, a trajectory-based validator achieves a false-certificate probability of at most one in 1,048,576 and a nominal acceptance probability of at least 95 percent, using no more than 720,160 source copies. Under the same preparation and physical-response promises, every validator restricted to terminal errors and meeting the same acceptance requirement needs more than 1,992,371 source copies in expectation. At the exact nominal device, an uncapped trajectory-based test accepts almost surely with expected consumption below 254,746 copies. A separate robustness analysis extends likelihood-test validity to a quantified class of conditional response deviations. Finite-cap guarantees and expected stopping costs remain explicitly distinguished. The results demonstrate a certified resource advantage from access to retained classical measurement trajectories, rather than merely an improvement over one chosen terminal-error test. Supporting materials provide the fixed reader, exact certificates and reproducibility procedures. All guarantees depend on the stated preparation, response, information-access and deployment-stability assumptions. Certification concerns the nominated reader’s decision error; it does not establish complete quantum-instrument equivalence or identify an underlying source. The analysis uses standard quantum probabilities within Shadow Theory’s research programme.

•Oct 28, 2026•0 citations

Symmetries between measurements in quantum mechanics

H. Chau Nguyen, Sébastien Designolle, Barakat, Mohamed +1 more

Symmetries are a key concept to connect mathematical elegance with physical insight. We consider measurement assemblages in quantum mechanics and show how their symmetry can be described by means of the so-called discrete bundles. It turns out that many measurement assemblages used in quantum information theory as well as for studying the foundations of quantum mechanics are entirely determined by symmetry; moreover, starting from a certain symmetry group, novel types of measurement sets can be constructed. The insight gained from symmetry allows us to easily determine whether the measurements in the set are incompatible under noisy conditions, i.e., whether they can be regarded as genuinely distinct ones. In addition, symmetry enables us to identify finite sets of measurements having a high sensitivity to reveal the quantumness of distributed quantum states.

arXiv:2003.12553•Mar 27, 2020•21 citations
Symmetry reduces the capacity of a quantum learning model, but the imposed group must match both the measured information and the label transformation. We establish a finite-measurement theory for inferring this group from candidate transformations. The central structural result identifies observable-invisible transformations with the stabilizer of a projected state whenever the probe span is invariant. It turns recovered generators into a valid subgroup and identifies the continuous invisible space with its Lie algebra. For finite dictionaries, an unbiased shadow statistic distinguishes zero from positive squared expectation discrepancies with an inverse-gap measurement rate, improving the inverse-square-gap rate of uniform discrepancy estimation. A commuting qubit lower bound proves the gap dependence optimal at fixed snapshot scale, and simultaneous intervals support data-dependent tolerances. Task validation then tests either the joint distribution through a characteristic kernel or its encoded mean through a classical--quantum discrepancy. An exact group-average identity relates the latter to joint-state asymmetry and specifies its conversion to binary task breaking mass. Projection bias quantifies the cost of excessive symmetry, while an ℓ1\ell_1ℓ1​ readout bound quantifies the capacity gained by relaxing it. At an invariant pure-state backbone, retained and nontrivial breaking sectors are Fisher-orthogonal. Ising-chain calculations connect finite-shot recovery, label-dependent symmetry, and physical sector drift. These results determine which symmetry the measurements support and provide the statistical and geometric basis for a subsequent release decision.
Hard symmetry constraints reduce model complexity, but can also erase label information. Statistical symmetry release determines when finite data and quantum measurements justify relaxing such a constraint, which directions to open, and how far to move. We connect global signal detection to local, loss-dependent improvement. A two-copy twirl--swap gate estimates task information in the symmetry-breaking complement with a dimension-independent copy count under paired-state and group-unitary access; reweighting the same records resolves representation sectors. An exact duality distinguishes this Hilbert--Schmidt signal from the larger signal accessible to bounded-outcome readouts. Local improvement is governed by the release gradient and a loss-corrected double-commutator matrix. Simultaneous confidence bounds convert empirical direction selection into certified descent, using either shared Pauli measurements or scalar probes with state-independent truncation bounds. Gaussian testing lower bounds quantify the cost of searching over unknown directions in the calibrated local experiment. Independent validation controls adaptively generated models, and a fast squared-loss bound preserves the approximation--estimation rate of a nested release path. On an eight-qubit Ising model, shared measurements certify release with 6300 times fewer shots than the specified scalar estimator on the tested budget grids. Quotient quantum natural gradient then controls parameter redundancy during training. Together, these results turn symmetry relaxation into a statistically justified model-selection decision.
Measuring a quantum computation in a basis adapted to a symmetry it carries reduces the repeated measurements, commonly referred to as ``shots'', needed to read a statistical answer. Detecting the symmetry a quantum state carries has many uses: certifying a claimed symmetry, identifying a conserved-charge sector, flagging symmetry-breaking as an error signature, and selecting a compression or readout basis; shot-count reduction is developed here as one exemplary case. Existing methods assume the symmetry is known in advance; we remove that assumption. When it is unknown, the carried symmetry is discovered from the data by a symmetry test that scores candidate groups, and the largest passing group is exploited as the measurement basis. We state the pipeline precisely, prove the selection rule is unbiased, and charge discovery in full. Two conditions are treated, both detected by the same score with a different projection: a weak condition, commutation with the representation, and a strong condition, confinement to a single charge sector, the distinction drawn in the quantum-reference-frame literature. A single circuit, a controlled twirl followed by a SWAP test, discovers both: discarding the group register tests the weak condition, post-selecting it the strong one. The framework is general over finite groups, with cyclic (Fourier), dihedral, and symmetric-group (Schur-Weyl) examples; strong confinement to the symmetric, or Dicke, subspace is an exponential reduction. Seeded demonstrations show the loop wins net of discovery: weak matching on momentum readout reduces shots by a factor widening from ten to several thousand, and strong matching on a two-system target by a further factor of the subsystem size. Blind symmetry matching is a practical primitive for the common case where the matched basis cannot be written down in advance.
Generative learning of a quantum measurement distribution from finite data requires choosing a model capacity that balances representation accuracy against estimation cost. We develop a bias-variance framework that decomposes the expected population Kullback-Leibler error at model capacity sss and sample size NNN as E(s,N)=B(s)+V(s,N)E(s,N)=B(s)+V(s,N)E(s,N)=B(s)+V(s,N), with representation bias BBB and a variance term VVV capturing the mean estimation error. In the well-sampled regime, V(s,N)≃[NC(s)]−1V(s,N)\simeq[NC(s)]^{-1}V(s,N)≃[NC(s)]−1, and exponential or algebraic laws for BBB and CCC yield four scaling templates for the optimal error, from inverse powers of NNN to inverse powers of ln⁡N\ln NlnN. For local autoregressive models, the context radius sets the model capacity, and BBB is the summed conditional mutual information lost by truncating the context. For a smoothed histogram learner, we derive an exact finite-sample estimation cost that accounts for rarely observed contexts and recovers the parameter-count law in the well-sampled regime. For transverse-field Ising Born distributions, the independently evaluated bias and estimation cost predict both the optimal context radius and the optimal error. In the well-sampled regime, the estimation cost grows exponentially with context radius. Its competition with approximately exponential bias decay in the gapped regimes predicts power-law error decay in NNN, while algebraic bias decay at criticality predicts asymptotic inverse-power decay in ln⁡N\ln NlnN. Bulk-site results are consistent with the corresponding finite-sample predictions. These results connect the structure of quantum measurement distributions to the model capacity justified by finite data.
Quantum machine learning (QML) models are aimed at learning from data encoded in quantum states.Recently, it has been shown that models with little to no inductive biases (i.e., with no assumptions about the problem embedded in the model) are likely to have trainability and generalization issues, especially for large problem sizes.As such, it is fundamental to develop schemes that encode as much information as available about the problem at hand.In this work we present a simple, yet powerful, framework where the underlying invariances in the data are used to build QML models that, by construction, respect those symmetries.These so-called group-invariant models produce outputs that remain invariant under the action of any element of the symmetry group G associated with the dataset.We present theoretical results underpinning the design of G-invariant models, and exemplify their application through several paradigmatic QML classification tasks, including cases when G is a continuous Lie group and also when it is a discrete symmetry group.Notably, our framework allows us to recover, in an elegant way, several well-known algorithms for the literature, as well as to discover new ones.Taken together, we expect that our results will help pave the way towards a more geometric and group-theoretic approach to QML model design.
This paper develops task-relative reader certification within Shadow Theory’s source–readout programme. It asks how many source copies are needed to validate a fixed quantum reader, and when access to its retained measurement records reduces that cost compared with observing only its final correct-or-incorrect decisions. The reader is fixed before validation and must return a sign after each complete experiment. A trusted evaluator knows the preparation label for scoring, while the reader does not. The analysis distinguishes terminal-error observations, records with trusted ancillary information, and readable measurement trajectories governed by a shared physical response model. For terminal-error validation, the paper establishes exact finite-budget tests and sequential likelihood tests, together with nearly matching information-theoretic lower bounds on expected source consumption. An unrestricted-record result shows why additional archived data alone need not improve certification: an advantage requires specified information or response constraints. A separate trusted-seed construction gives an exact information-projection test. The central quantitative comparison concerns a fixed fourteen-copy reader in a trusted shared-visibility family. To certify a maximum label error of one percent, a trajectory-based validator achieves a false-certificate probability of at most one in 1,048,576 and a nominal acceptance probability of at least 95 percent, using no more than 720,160 source copies. Under the same preparation and physical-response promises, every validator restricted to terminal errors and meeting the same acceptance requirement needs more than 1,992,371 source copies in expectation. At the exact nominal device, an uncapped trajectory-based test accepts almost surely with expected consumption below 254,746 copies. A separate robustness analysis extends likelihood-test validity to a quantified class of conditional response deviations. Finite-cap guarantees and expected stopping costs remain explicitly distinguished. The results demonstrate a certified resource advantage from access to retained classical measurement trajectories, rather than merely an improvement over one chosen terminal-error test. Supporting materials provide the fixed reader, exact certificates and reproducibility procedures. All guarantees depend on the stated preparation, response, information-access and deployment-stability assumptions. Certification concerns the nominated reader’s decision error; it does not establish complete quantum-instrument equivalence or identify an underlying source. The analysis uses standard quantum probabilities within Shadow Theory’s research programme.
Symmetries are a key concept to connect mathematical elegance with physical insight. We consider measurement assemblages in quantum mechanics and show how their symmetry can be described by means of the so-called discrete bundles. It turns out that many measurement assemblages used in quantum information theory as well as for studying the foundations of quantum mechanics are entirely determined by symmetry; moreover, starting from a certain symmetry group, novel types of measurement sets can be constructed. The insight gained from symmetry allows us to easily determine whether the measurements in the set are incompatible under noisy conditions, i.e., whether they can be regarded as genuinely distinct ones. In addition, symmetry enables us to identify finite sets of measurements having a high sensitivity to reveal the quantumness of distributed quantum states.