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:2610.03690

Universal Bounds for Out-of-Distribution Unitary Learning

Joachim Favre, Armando Angrisani, Zoë Holmes

quant-phSubmitted Oct 2, 2026• Announced Oct 5, 2026• 0 citations• Revised Oct 29, 2026 (v2)
v1 · Oct 2, 2026v2 · Oct 29, 2026
arXivHTMLPDF

Abstract

How much can the action of an unknown unitary dynamics on one family of states reveal about its action elsewhere? We develop a general framework for out-of-distribution quantum dynamics learning based on the first and second moments of the input distribution. These define a notion of the bias and expressivity of an ensemble, which together control generalization between arbitrary mixed-state training and testing distributions. Our framework shows that only studying the action of a unitary on random real states can learn its action on random complex states, that tensor products of unbiased pure-state ensembles preserve expressivity, and that single-qubit risks are independent of bias. It also recovers earlier locally scrambling results as loose special cases and yields tight product-to-Haar bounds. We conclude with a series of no-go results and limited generalization bounds for learning certain channels, which further serve to underscore the distinctive role of unitarity in enabling out-of-distribution generalization.

AI Summary

The paper asks when small average error in learning a quantum process on one input ensemble guarantees small error on another. It studies squared Hilbert–Schmidt output loss, equal to infidelity for unitary processes on pure inputs; finite-sample learning is treated separately. For unitary targets and models, vectorization expresses risk through $M(\mathcal P)=2^n\mathbb E[\rho\otimes\rho^{\mathsf T}]$. Separating identity and traceless components defines bias $\nu$ and expressivity $\eta=\bar\gamma-\lambda_{\max}(\mathcal S)$, where $\bar\gamma$ is average purity. Spectral bounds give $R_{\rm test}\leq(R_{\rm train}+\nu_{\rm train})/\eta_{\rm train}+\nu_{\rm test}$ when $\eta_{\rm train}>0$. Jointly Pauli-diagonal, unbiased ensembles admit tight eigenvalue-ratio comparisons. Applications include real-Haar training controlling complex-Haar risk with tight overhead $1+1/(2^n+1)$, preservation of expressivity under tensor products of unbiased pure-state ensembles, and tight product-Haar-to-global-Haar overhead approaching $3/2$ rather than the previous $2$. Single-qubit risk is independent of bias. Tight noisy-to-clean comparisons have constant overhead for local depolarizing rate $O(1/n)$, polynomial overhead for $O(\log n/n)$, and exponential overhead at fixed positive rate. Explicit channel counterexamples require exponential global-Haar-to-product-Haar overhead, or show zero real-input risk despite constant complex-input risk. For Pauli channels with combined support $s$, arbitrary-input risk is bounded by $s(1+2^{-n})$ times global-Haar risk or $s^2$ times product-Haar risk. Except for these sparse-channel guarantees, results concern average rather than worst-case performance; appreciable bias or low expressivity can make the general bounds uninformative.

Little sign of AI-generated textAI use disclosed
In the past month, ChatGPT helped us find no-go results to rule out the hoped-for general channel extension. It also helped with the final writing sprint.

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

Comments
13+62 pages, 1+1 figures. Edit: Added some results from the appendices to the main text, added a visualization of expressivity to the appendices, and fixed some typos

Related papers

Mixed State Deep Thermalization under Generic Quantum Errors

Xie-Hang Yu, Pavel Kos

Pure-state deep thermalization predicts that, after sufficient scrambling, projected ensembles approach universal distributions that contain information beyond the reduced density matrix. In realistic quantum systems, however, noise is unavoidable and the projected states are generally mixed. Whether mixed-state deep thermalization admits an analogous universal limiting distribution has remained unclear. Here we answer this question for quantum dynamics containing local quantum channels, i.e., errors. We show that the late-time mixed-state projected ensemble is completely determined by the normalized Choi state of the error channel and is universal, independent of the microscopic details of the underlying unitary dynamics. We establish this result analytically for dual-unitary circuits, global Haar-random dynamics, and local Haar-random circuits at large local dimension, and verify it numerically in qubit circuits and kicked Ising dynamics. In a solvable setting, we further find exponentially fast convergence to the limiting ensemble. Our results extend deep thermalization to noisy quantum dynamics and establish a direct correspondence between quantum errors and universal random mixed-state ensembles.

quant-pharXiv:2610.31580•Oct 23, 2026•2 citations

Out-of-distribution generalization for learning quantum dynamics

Matthias C. Caro, Hsin-Yuan Huang, Nic Ezzell +5 more

Generalization bounds are a critical tool to assess the training data requirements of Quantum Machine Learning (QML). Recent work has established guarantees for in-distribution generalization of quantum neural networks (QNNs), where training and testing data are drawn from the same data distribution. However, there are currently no results on out-of-distribution generalization in QML, where we require a trained model to perform well even on data drawn from a different distribution to the training distribution. Here, we prove out-of-distribution generalization for the task of learning an unknown unitary. In particular, we show that one can learn the action of a unitary on entangled states having trained only product states. Since product states can be prepared using only single-qubit gates, this advances the prospects of learning quantum dynamics on near term quantum hardware, and further opens up new methods for both the classical and quantum compilation of quantum circuits.

arXiv:2204.10268•Nature Communications•Jul 5, 2023•110 citations

Quantum state learning beyond approximate unitary designs

Gyungmin Cho, Changhun Oh, Dohun Kim

Approximate unitary designs reproduce the statistics of Haar-random unitaries to a given order and accuracy. Recent constructions realize such designs with logarithmic-depth circuits, enabling shallow measurement protocols for various quantum state-learning tasks while preserving performance. These results raise the question of whether approximate designs can replace exact designs more generally. We show that even exponentially small design error need not preserve the learning guarantees of exact designs. This motivates deriving learning guarantees directly from the measurement circuit structure. For observable estimation with classical shadows, we prove that logarithmic-depth two-layer Clifford circuits yield an unbiased estimator matching the global Clifford variance scaling for every state and Hermitian observable. Beyond observable estimation, this bound allows shallow measurements to retain global Clifford guarantees for other tasks, including setting-efficient tomography, mixed-state metrology, and stabilizer structure learning. We complement these statistical guarantees with a compact, exact tensor-network representation of the inverse shadow channel. When measurement bases are reused, approximate unitary designs of arbitrarily high order need not uniformly match the Haar variance in the many-shot limit. For the all-to-all random two-local circuits considered, doing so requires nearly linear depth. Together, our results reveal the capabilities and limitations of shallow quantum state learning, highlighting the distinction between approximating Haar randomness and reproducing its learning guarantees.

quant-pharXiv:2609.39994•Oct 1, 2026•2 citations

Predicting quantum channels over general product distributions

Sitan Chen, Pont, Jaume de Dios, Jun-Ting Hsieh +3 more

We investigate the problem of predicting the output behavior of unknown quantum channels. Given query access to an $n$-qubit channel $E$ and an observable $O$, we aim to learn the mapping \begin{equation*} ρ\mapsto \mathrm{Tr}(O E[ρ]) \end{equation*} to within a small error for most $ρ$ sampled from a distribution $D$. Previously, Huang, Chen, and Preskill proved a surprising result that even if $E$ is arbitrary, this task can be solved in time roughly $n^{O(\log(1/ε))}$, where $ε$ is the target prediction error. However, their guarantee applied only to input distributions $D$ invariant under all single-qubit Clifford gates, and their algorithm fails for important cases such as general product distributions over product states $ρ$. In this work, we propose a new approach that achieves accurate prediction over essentially any product distribution $D$, provided it is not "classical" in which case there is a trivial exponential lower bound. Our method employs a "biased Pauli analysis," analogous to classical biased Fourier analysis. Implementing this approach requires overcoming several challenges unique to the quantum setting, including the lack of a basis with appropriate orthogonality properties. The techniques we develop to address these issues may have broader applications in quantum information.

arXiv:2409.03684•Sep 5, 2024•8 citations

Characterizing quantum channels from local-unitary invariants

Salwa Shaglel, Satoya Imai

We develop systematic frameworks for characterizing the entanglement properties of two-qubit channels beyond unitary settings. We introduce averaged local-unitary invariants, referred to as moments, obtained from Haar integrals over input states or unitaries. These moments provide computable descriptions of how a quantum channel can create, preserve, or destroy bipartite entanglement. We first show that second-order moments yield criteria for non-entangling and entanglement-breaking channels, which allow us to detect entanglement-creating and entanglement-preserving channels. We then demonstrate that higher-order moments can capture additional information and distinguish channels beyond second-order moments alone. Finally, we show that combinations of moments associated with different channel families improve the discrimination of locally inequivalent two-qubit unitaries.

quant-pharXiv:2606.03722•Jun 3, 2026•0 citations

Out-of-Distribution Generalization for Learning Quantum Channels with Low-Energy Coherent States

Jason L. Pereira, Quntao Zhuang, Leonardo Banchi

When experimentally learning the action of a continuous-variable quantum process by probing it with inputs, there will often be some restriction on the input states used. One experimentally simple way to probe a quantum channel is to use low-energy coherent states. Learning a quantum channel in this way presents difficulties, due to the fact that two channels may act similarly on low-energy inputs but very differently for high-energy inputs. They may also act similarly on coherent-state inputs but differently on nonclassical inputs. Extrapolating the behavior of a channel for more general input states from its action on the far more limited set of low-energy coherent states is a case of out-of-distribution generalization. To be sure that such generalization gives meaningful results, one needs to relate error bounds for the training set to bounds that are valid for all inputs. We show that for any pair of channels that act sufficiently similarly on low-energy coherent-state inputs, one can bound how different the input-output relations are for any (high-energy or highly nonclassical) input. This proves that out-of-distribution generalization is always possible for learning quantum channels using low-energy coherent states, as long as enough samples are used.

arXiv:2502.04454•PRX Quantum•Aug 13, 2025•2 citations
How much can the action of an unknown unitary dynamics on one family of states reveal about its action elsewhere? We develop a general framework for out-of-distribution quantum dynamics learning based on the first and second moments of the input distribution. These define a notion of the bias and expressivity of an ensemble, which together control generalization between arbitrary mixed-state training and testing distributions. Our framework shows that only studying the action of a unitary on random real states can learn its action on random complex states, that tensor products of unbiased pure-state ensembles preserve expressivity, and that single-qubit risks are independent of bias. It also recovers earlier locally scrambling results as loose special cases and yields tight product-to-Haar bounds. We conclude with a series of no-go results and limited generalization bounds for learning certain channels, which further serve to underscore the distinctive role of unitarity in enabling out-of-distribution generalization.
The paper asks when small average error in learning a quantum process on one input ensemble guarantees small error on another. It studies squared Hilbert–Schmidt output loss, equal to infidelity for unitary processes on pure inputs; finite-sample learning is treated separately.
For unitary targets and models, vectorization expresses risk through M(P)=2nE[ρ⊗ρT]M(\mathcal P)=2^n\mathbb E[\rho\otimes\rho^{\mathsf T}]M(P)=2nE[ρ⊗ρT]. Separating identity and traceless components defines bias ν\nuν and expressivity η=γˉ−λmax⁡(S)\eta=\bar\gamma-\lambda_{\max}(\mathcal S)η=γˉ​−λmax​(S), where γˉ\bar\gammaγˉ​ is average purity. Spectral bounds give Rtest≤(Rtrain+νtrain)/ηtrain+νtestR_{\rm test}\leq(R_{\rm train}+\nu_{\rm train})/\eta_{\rm train}+\nu_{\rm test}Rtest​≤(Rtrain​+νtrain​)/ηtrain​+νtest​ when ηtrain>0\eta_{\rm train}>0ηtrain​>0. Jointly Pauli-diagonal, unbiased ensembles admit tight eigenvalue-ratio comparisons.
Applications include real-Haar training controlling complex-Haar risk with tight overhead 1+1/(2n+1)1+1/(2^n+1)1+1/(2n+1), preservation of expressivity under tensor products of unbiased pure-state ensembles, and tight product-Haar-to-global-Haar overhead approaching 3/23/23/2 rather than the previous 222. Single-qubit risk is independent of bias. Tight noisy-to-clean comparisons have constant overhead for local depolarizing rate O(1/n)O(1/n)O(1/n), polynomial overhead for O(log⁡n/n)O(\log n/n)O(logn/n), and exponential overhead at fixed positive rate.
Explicit channel counterexamples require exponential global-Haar-to-product-Haar overhead, or show zero real-input risk despite constant complex-input risk. For Pauli channels with combined support sss, arbitrary-input risk is bounded by s(1+2−n)s(1+2^{-n})s(1+2−n) times global-Haar risk or s2s^2s2 times product-Haar risk. Except for these sparse-channel guarantees, results concern average rather than worst-case performance; appreciable bias or low expressivity can make the general bounds uninformative.
Pure-state deep thermalization predicts that, after sufficient scrambling, projected ensembles approach universal distributions that contain information beyond the reduced density matrix. In realistic quantum systems, however, noise is unavoidable and the projected states are generally mixed. Whether mixed-state deep thermalization admits an analogous universal limiting distribution has remained unclear. Here we answer this question for quantum dynamics containing local quantum channels, i.e., errors. We show that the late-time mixed-state projected ensemble is completely determined by the normalized Choi state of the error channel and is universal, independent of the microscopic details of the underlying unitary dynamics. We establish this result analytically for dual-unitary circuits, global Haar-random dynamics, and local Haar-random circuits at large local dimension, and verify it numerically in qubit circuits and kicked Ising dynamics. In a solvable setting, we further find exponentially fast convergence to the limiting ensemble. Our results extend deep thermalization to noisy quantum dynamics and establish a direct correspondence between quantum errors and universal random mixed-state ensembles.
Generalization bounds are a critical tool to assess the training data requirements of Quantum Machine Learning (QML). Recent work has established guarantees for in-distribution generalization of quantum neural networks (QNNs), where training and testing data are drawn from the same data distribution. However, there are currently no results on out-of-distribution generalization in QML, where we require a trained model to perform well even on data drawn from a different distribution to the training distribution. Here, we prove out-of-distribution generalization for the task of learning an unknown unitary. In particular, we show that one can learn the action of a unitary on entangled states having trained only product states. Since product states can be prepared using only single-qubit gates, this advances the prospects of learning quantum dynamics on near term quantum hardware, and further opens up new methods for both the classical and quantum compilation of quantum circuits.
Approximate unitary designs reproduce the statistics of Haar-random unitaries to a given order and accuracy. Recent constructions realize such designs with logarithmic-depth circuits, enabling shallow measurement protocols for various quantum state-learning tasks while preserving performance. These results raise the question of whether approximate designs can replace exact designs more generally. We show that even exponentially small design error need not preserve the learning guarantees of exact designs. This motivates deriving learning guarantees directly from the measurement circuit structure. For observable estimation with classical shadows, we prove that logarithmic-depth two-layer Clifford circuits yield an unbiased estimator matching the global Clifford variance scaling for every state and Hermitian observable. Beyond observable estimation, this bound allows shallow measurements to retain global Clifford guarantees for other tasks, including setting-efficient tomography, mixed-state metrology, and stabilizer structure learning. We complement these statistical guarantees with a compact, exact tensor-network representation of the inverse shadow channel. When measurement bases are reused, approximate unitary designs of arbitrarily high order need not uniformly match the Haar variance in the many-shot limit. For the all-to-all random two-local circuits considered, doing so requires nearly linear depth. Together, our results reveal the capabilities and limitations of shallow quantum state learning, highlighting the distinction between approximating Haar randomness and reproducing its learning guarantees.
We investigate the problem of predicting the output behavior of unknown quantum channels. Given query access to an nnn-qubit channel EEE and an observable OOO, we aim to learn the mapping \begin{equation*} ρ\mapsto \mathrm{Tr}(O E[ρ]) \end{equation*} to within a small error for most ρρρ sampled from a distribution DDD. Previously, Huang, Chen, and Preskill proved a surprising result that even if EEE is arbitrary, this task can be solved in time roughly nO(log⁡(1/ε))n^{O(\log(1/ε))}nO(log(1/ε)), where εεε is the target prediction error. However, their guarantee applied only to input distributions DDD invariant under all single-qubit Clifford gates, and their algorithm fails for important cases such as general product distributions over product states ρρρ. In this work, we propose a new approach that achieves accurate prediction over essentially any product distribution DDD, provided it is not "classical" in which case there is a trivial exponential lower bound. Our method employs a "biased Pauli analysis," analogous to classical biased Fourier analysis. Implementing this approach requires overcoming several challenges unique to the quantum setting, including the lack of a basis with appropriate orthogonality properties. The techniques we develop to address these issues may have broader applications in quantum information.
We develop systematic frameworks for characterizing the entanglement properties of two-qubit channels beyond unitary settings. We introduce averaged local-unitary invariants, referred to as moments, obtained from Haar integrals over input states or unitaries. These moments provide computable descriptions of how a quantum channel can create, preserve, or destroy bipartite entanglement. We first show that second-order moments yield criteria for non-entangling and entanglement-breaking channels, which allow us to detect entanglement-creating and entanglement-preserving channels. We then demonstrate that higher-order moments can capture additional information and distinguish channels beyond second-order moments alone. Finally, we show that combinations of moments associated with different channel families improve the discrimination of locally inequivalent two-qubit unitaries.
When experimentally learning the action of a continuous-variable quantum process by probing it with inputs, there will often be some restriction on the input states used. One experimentally simple way to probe a quantum channel is to use low-energy coherent states. Learning a quantum channel in this way presents difficulties, due to the fact that two channels may act similarly on low-energy inputs but very differently for high-energy inputs. They may also act similarly on coherent-state inputs but differently on nonclassical inputs. Extrapolating the behavior of a channel for more general input states from its action on the far more limited set of low-energy coherent states is a case of out-of-distribution generalization. To be sure that such generalization gives meaningful results, one needs to relate error bounds for the training set to bounds that are valid for all inputs. We show that for any pair of channels that act sufficiently similarly on low-energy coherent-state inputs, one can bound how different the input-output relations are for any (high-energy or highly nonclassical) input. This proves that out-of-distribution generalization is always possible for learning quantum channels using low-energy coherent states, as long as enough samples are used.