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:2601.12651

Learning at the Edge of Causality: Optimal Learning-Sample Complexity from No-Signaling Constraints

Jeongho Bang, Kyoungho Cho, Jeongwoo Jae

quant-phSubmitted Jan 19, 2026• Announced Jan 20, 2026• 3 citations
arXivHTMLPDF

Abstract

What ultimately fixes the sample cost of quantum learning -- algorithmic ingenuity or physical law? We study this question in an arena where computation, learning, and causality collide. A twist on Grover's search that reflects about an a priori unknown state can collapse the query complexity from $O(\sqrt{N})$ to $O(\log N)$ over a search space $N$, i.e., an exponential speedup. Yet, standard quantum theory forbids such a unknown-state reflection (no-reflection theorem). We therefore build a state-learning-assisted architecture, called ``amplify-learn,'' which alternates the coherent amplitude amplification with state learning. Embedding this amplify-learn into the Bao-Bouland-Jordan no-signaling framework, we show that the logarithmic-round dream would open a super-luminal communication channel unless each round expends the learning-sample and reflection-circuit budgets scaling at least as $Ω(\sqrt{N}/\log N)$. In parallel, we derive tight computational learning-theoretic sample bounds for learning circuit-generated pure states, revealing a state-universal ansatz ``lock'' at order $N$ in the worst case. The dramatic closure is that no-signaling does not merely veto the unphysical primitive, but it fixes the only consistent reflection-circuit complexity, and feeding this causality-enforced complexity into the computational learning bound makes it collapse onto the very same $\sqrt{N}/\log N$ scaling demanded by no-signaling alone. No-signaling thus acts as a regulator of learnability: a constraint that mediates between physics and computation, welding query, gate, and sample complexities into a single causality-compatible triangle.

Comments
Main text (10 page, 2 figures) / Supplementary Information (36 pages, 1 figure)

Related papers

Quantum Occam Learning: Sample-Supported Expressibility for Circuit-Based Quantum Learning

Jeongho Bang, Kyoungho Cho, Jeongwoo Jae

A central principle in quantum machine learning is that an ansatz should be expressive enough to represent the quantum data of interest. Yet, the expressibility is statistically meaningful only insofar as it can be learned from finitely many copies of an unknown quantum state. In this work, we develop an information-theoretic Occam theory for quantum data generated by finite-size quantum circuits. For the class $S_{n,G}$ of $n$-qubit pure states preparable with at most $G$ two-qubit gates, a metric-entropy argument gives the realizable sample law $\widetildeΘ(G/ε^2)$ in the circuit-limited regime. For an arbitrary source $\hatρ$, we introduce the best $G$-gate approximation error $d_G(\hatρ)$ and the approximate circuit complexity $C_η(\hatρ)$. We prove an agnostic quantum Occam theorem: with $M$ copies, one can learn up to the best $G$-gate approximation error plus a statistical penalty $\widetilde{O}(\sqrt{G/M})$. We then remove the need to know $G$ in advance through an adaptive model-selection theorem whose oracle inequality selects the circuit complexity justified by the data. Matching lower bounds yield a sample-supported expressibility law: at trace-distance accuracy $ε$, $M$ samples can support only $G_{\rm supported} \simeq Mε^2$ gates, up to logarithmic factors and tomography saturation at $2^n$. Thus, the circuit complexity becomes an adaptive statistical resource rather than a static promise. Our framework turns bounded circuit complexity into a model-selection principle for quantum machine learning.

quant-pharXiv:2606.12211•Jun 11, 2026•0 citations

Cloning is as Hard as Learning for Stabilizer States

Nikhil Bansal, Matthias C. Caro, Gaurav Mahajan

The impossibility of simultaneously cloning non-orthogonal states lies at the foundations of quantum theory. Even when allowing for approximation errors, cloning an arbitrary unknown pure state requires as many initial copies as needed to fully learn the state. Rather than arbitrary unknown states, modern quantum learning theory often considers structured classes of states and exploits such structure to develop learning algorithms that outperform general-state tomography. This raises the question: How do the sample complexities of learning and cloning relate for such structured classes? We answer this question for an important class of states. Namely, for $n$-qubit stabilizer states, we show that the optimal sample complexity of cloning is $Θ(n)$. Thus, also for this structured class of states, cloning is as hard as learning. To prove these results, we use representation-theoretic tools in the recently proposed Abelian State Hidden Subgroup framework and a new structured version of the recently introduced random purification channel to relate stabilizer state cloning to a variant of the sample amplification problem for probability distributions that was recently introduced in classical learning theory. This allows us to obtain our cloning lower bounds by proving new sample amplification lower bounds for classes of distributions with an underlying linear structure. Our results provide a more fine-grained perspective on No-Cloning theorems, opening up connections from foundations to quantum learning theory and quantum cryptography.

quant-pharXiv:2604.15269•Apr 17, 2026•4 citations

Learning Quantum States and Unitaries of Bounded Gate Complexity

Haimeng Zhao, Laura Lewis, Ishaan Kannan +3 more

While quantum state tomography is notoriously hard, most states hold little interest to practically minded tomographers. Given that states and unitaries appearing in nature are of bounded gate complexity, it is natural to ask if efficient learning becomes possible. In this work, we prove that to learn a state generated by a quantum circuit with G two-qubit gates to a small trace distance, a sample complexity scaling linearly in G is necessary and sufficient. We also prove that the optimal query complexity to learn a unitary generated by G gates to a small average-case error scales linearly in G . While sample-efficient learning can be achieved, we show that under reasonable cryptographic conjectures, the computational complexity for learning states and unitaries of gate complexity G must scale exponentially in G . We illustrate how these results establish fundamental limitations on the expressivity of quantum machine-learning models and provide new perspectives on no-free-lunch theorems in unitary learning. Together, our results answer how the complexity of learning quantum states and unitaries relate to the complexity of creating these states and unitaries. Published by the American Physical Society 2024

arXiv:2310.19882•PRX Quantum•Oct 16, 2024•70 citations

Advantage of Sample Complexity in Quantum PAC Learning Requires Inverse Access to State-Preparation Unitaries

Natsuto Isogai, Satoshi Yoshida, Mio Murao

Whether quantum computation can reduce the amount of data required for conventional machine learning is a central problem in quantum machine learning. In probably approximately correct (PAC) learning, a learner receives training examples sampled from an unknown probability distribution. Quantum PAC learning extends this framework by allowing access to quantum examples, which are quantum states that coherently encode this distribution, or to unitaries that prepare quantum examples, with or without inverse access. When only copies of quantum examples are available, the optimal worst-case sample complexity asymptotically matches that of classical learning. In contrast, access to both a preparation unitary and its inverse can improve the accuracy dependence of query complexity. However, it has remained open whether access to the preparation unitary alone suffices for this improvement. In this work, we resolve this question by determining the optimal query complexity with forward-only access, taking the worst case over compatible preparation unitaries and their dimensions. In both realizable and agnostic PAC learning, this complexity matches, up to constant factors, the optimal sample complexity achievable with classical examples or copies of quantum examples. To prove these results, we construct, for any algorithm with forward-only access, a simulator that approximates the algorithm's Haar-averaged output state using as many copies of the prepared state as the algorithm makes queries. These results show that inverse access is essential for the known improvement in accuracy dependence in this worst-case setting. Beyond PAC learning, our reduction provides a general tool for transferring lower bounds for state copies to query lower bounds for forward-only access to the corresponding preparation unitaries.

quant-pharXiv:2609.38403•Oct 1, 2026•1 citation

Sample complexity of learning parametric quantum circuits

Haoyuan Cai, Qi Ye, Dong-Ling Deng

Abstract Quantum computers hold unprecedented potentials for machine learning applications. Here, we prove that physical quantum circuits are probably approximately correct learnable on a quantum computer via empirical risk minimization: to learn a parametric quantum circuit with at most n c gates and each gate acting on a constant number of qubits, the sample complexity is bounded by O ~ ( n c + 1 ) . In particular, we explicitly construct a family of variational quantum circuits with O(n c+1) elementary gates arranged in a fixed pattern, which can represent all physical quantum circuits consisting of at most n c elementary gates. Our results provide a valuable guide for quantum machine learning in both theory and practice.

arXiv:2107.09078•Quantum Science and Technology•Jan 26, 2022•29 citations

Quantum advantage in learning single mode bosonic channels

Angela Anna Baiju, Aritra Das, Özlem Erkılıç +7 more

Quantum resources can dramatically reduce the data required to learn physical systems, with exponential improvements in sample complexity demonstrated in several quantum learning tasks. However, these advantages have typically relied on quantum resources that scale with problem complexity, most notably increasing system dimension or entanglement. This raises a fundamental question: can exponential quantum learning advantages arise within a fixed, unentangled quantum system? In this paper, we address this question by considering the learning of an unknown random-displacement distribution whose complexity is determined not by the dimensionality of the physical system, but by the Fourier resolution of its features. We show that the quantum-limited noise of vacuum probes progressively obscures high-frequency features, leading to an exponential growth in sample complexity. We establish an information-theoretic lower bound for arbitrary classical-state probes and show that squeezing overcomes this classical limit by extending the accessible Fourier bandwidth. Experimentally, we demonstrate an exponential reduction in sample complexity using squeezed vacuum probes for both binary hypothesis testing and characteristic-function reconstruction. Our results show that a single bosonic mode can exhibit exponential quantum learning advantages without entanglement or an increase in system size, identifying accessible Fourier bandwidth as a fundamentally distinct resource for quantum-enhanced learning.

quant-pharXiv:2609.30374•Sep 28, 2026•2 citations
What ultimately fixes the sample cost of quantum learning -- algorithmic ingenuity or physical law? We study this question in an arena where computation, learning, and causality collide. A twist on Grover's search that reflects about an a priori unknown state can collapse the query complexity from O(N)O(\sqrt{N})O(N​) to O(log⁡N)O(\log N)O(logN) over a search space NNN, i.e., an exponential speedup. Yet, standard quantum theory forbids such a unknown-state reflection (no-reflection theorem). We therefore build a state-learning-assisted architecture, called amplify-learn,'' which alternates the coherent amplitude amplification with state learning. Embedding this amplify-learn into the Bao-Bouland-Jordan no-signaling framework, we show that the logarithmic-round dream would open a super-luminal communication channel unless each round expends the learning-sample and reflection-circuit budgets scaling at least as $Ω(\sqrt{N}/\log N)$. In parallel, we derive tight computational learning-theoretic sample bounds for learning circuit-generated pure states, revealing a state-universal ansatz lock'' at order NNN in the worst case. The dramatic closure is that no-signaling does not merely veto the unphysical primitive, but it fixes the only consistent reflection-circuit complexity, and feeding this causality-enforced complexity into the computational learning bound makes it collapse onto the very same N/log⁡N\sqrt{N}/\log NN​/logN scaling demanded by no-signaling alone. No-signaling thus acts as a regulator of learnability: a constraint that mediates between physics and computation, welding query, gate, and sample complexities into a single causality-compatible triangle.
A central principle in quantum machine learning is that an ansatz should be expressive enough to represent the quantum data of interest. Yet, the expressibility is statistically meaningful only insofar as it can be learned from finitely many copies of an unknown quantum state. In this work, we develop an information-theoretic Occam theory for quantum data generated by finite-size quantum circuits. For the class Sn,GS_{n,G}Sn,G​ of nnn-qubit pure states preparable with at most GGG two-qubit gates, a metric-entropy argument gives the realizable sample law Θ~(G/ε2)\widetildeΘ(G/ε^2)Θ(G/ε2) in the circuit-limited regime. For an arbitrary source ρ^\hatρρ^​, we introduce the best GGG-gate approximation error dG(ρ^)d_G(\hatρ)dG​(ρ^​) and the approximate circuit complexity Cη(ρ^)C_η(\hatρ)Cη​(ρ^​). We prove an agnostic quantum Occam theorem: with MMM copies, one can learn up to the best GGG-gate approximation error plus a statistical penalty O~(G/M)\widetilde{O}(\sqrt{G/M})O(G/M​). We then remove the need to know GGG in advance through an adaptive model-selection theorem whose oracle inequality selects the circuit complexity justified by the data. Matching lower bounds yield a sample-supported expressibility law: at trace-distance accuracy εεε, MMM samples can support only Gsupported≃Mε2G_{\rm supported} \simeq Mε^2Gsupported​≃Mε2 gates, up to logarithmic factors and tomography saturation at 2n2^n2n. Thus, the circuit complexity becomes an adaptive statistical resource rather than a static promise. Our framework turns bounded circuit complexity into a model-selection principle for quantum machine learning.
The impossibility of simultaneously cloning non-orthogonal states lies at the foundations of quantum theory. Even when allowing for approximation errors, cloning an arbitrary unknown pure state requires as many initial copies as needed to fully learn the state. Rather than arbitrary unknown states, modern quantum learning theory often considers structured classes of states and exploits such structure to develop learning algorithms that outperform general-state tomography. This raises the question: How do the sample complexities of learning and cloning relate for such structured classes? We answer this question for an important class of states. Namely, for nnn-qubit stabilizer states, we show that the optimal sample complexity of cloning is Θ(n)Θ(n)Θ(n). Thus, also for this structured class of states, cloning is as hard as learning. To prove these results, we use representation-theoretic tools in the recently proposed Abelian State Hidden Subgroup framework and a new structured version of the recently introduced random purification channel to relate stabilizer state cloning to a variant of the sample amplification problem for probability distributions that was recently introduced in classical learning theory. This allows us to obtain our cloning lower bounds by proving new sample amplification lower bounds for classes of distributions with an underlying linear structure. Our results provide a more fine-grained perspective on No-Cloning theorems, opening up connections from foundations to quantum learning theory and quantum cryptography.
While quantum state tomography is notoriously hard, most states hold little interest to practically minded tomographers. Given that states and unitaries appearing in nature are of bounded gate complexity, it is natural to ask if efficient learning becomes possible. In this work, we prove that to learn a state generated by a quantum circuit with G two-qubit gates to a small trace distance, a sample complexity scaling linearly in G is necessary and sufficient. We also prove that the optimal query complexity to learn a unitary generated by G gates to a small average-case error scales linearly in G . While sample-efficient learning can be achieved, we show that under reasonable cryptographic conjectures, the computational complexity for learning states and unitaries of gate complexity G must scale exponentially in G . We illustrate how these results establish fundamental limitations on the expressivity of quantum machine-learning models and provide new perspectives on no-free-lunch theorems in unitary learning. Together, our results answer how the complexity of learning quantum states and unitaries relate to the complexity of creating these states and unitaries. Published by the American Physical Society 2024
Whether quantum computation can reduce the amount of data required for conventional machine learning is a central problem in quantum machine learning. In probably approximately correct (PAC) learning, a learner receives training examples sampled from an unknown probability distribution. Quantum PAC learning extends this framework by allowing access to quantum examples, which are quantum states that coherently encode this distribution, or to unitaries that prepare quantum examples, with or without inverse access. When only copies of quantum examples are available, the optimal worst-case sample complexity asymptotically matches that of classical learning. In contrast, access to both a preparation unitary and its inverse can improve the accuracy dependence of query complexity. However, it has remained open whether access to the preparation unitary alone suffices for this improvement. In this work, we resolve this question by determining the optimal query complexity with forward-only access, taking the worst case over compatible preparation unitaries and their dimensions. In both realizable and agnostic PAC learning, this complexity matches, up to constant factors, the optimal sample complexity achievable with classical examples or copies of quantum examples. To prove these results, we construct, for any algorithm with forward-only access, a simulator that approximates the algorithm's Haar-averaged output state using as many copies of the prepared state as the algorithm makes queries. These results show that inverse access is essential for the known improvement in accuracy dependence in this worst-case setting. Beyond PAC learning, our reduction provides a general tool for transferring lower bounds for state copies to query lower bounds for forward-only access to the corresponding preparation unitaries.
Abstract Quantum computers hold unprecedented potentials for machine learning applications. Here, we prove that physical quantum circuits are probably approximately correct learnable on a quantum computer via empirical risk minimization: to learn a parametric quantum circuit with at most n c gates and each gate acting on a constant number of qubits, the sample complexity is bounded by O ~ ( n c + 1 ) . In particular, we explicitly construct a family of variational quantum circuits with O(n c+1) elementary gates arranged in a fixed pattern, which can represent all physical quantum circuits consisting of at most n c elementary gates. Our results provide a valuable guide for quantum machine learning in both theory and practice.
Quantum resources can dramatically reduce the data required to learn physical systems, with exponential improvements in sample complexity demonstrated in several quantum learning tasks. However, these advantages have typically relied on quantum resources that scale with problem complexity, most notably increasing system dimension or entanglement. This raises a fundamental question: can exponential quantum learning advantages arise within a fixed, unentangled quantum system? In this paper, we address this question by considering the learning of an unknown random-displacement distribution whose complexity is determined not by the dimensionality of the physical system, but by the Fourier resolution of its features. We show that the quantum-limited noise of vacuum probes progressively obscures high-frequency features, leading to an exponential growth in sample complexity. We establish an information-theoretic lower bound for arbitrary classical-state probes and show that squeezing overcomes this classical limit by extending the accessible Fourier bandwidth. Experimentally, we demonstrate an exponential reduction in sample complexity using squeezed vacuum probes for both binary hypothesis testing and characteristic-function reconstruction. Our results show that a single bosonic mode can exhibit exponential quantum learning advantages without entanglement or an increase in system size, identifying accessible Fourier bandwidth as a fundamentally distinct resource for quantum-enhanced learning.