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

Quantum Science and Technology

Trainability as differential information transmission in variational quantum circuits

Fouad Ailabouni, Roberto Casado Vara

Published Nov 5, 2026• 0 citations
PDF (CC BY)Publisher

Abstract

Abstract Understanding the origins of trainability in variational quantum circuits remains one of the central challenges in quantum machine learning. Existing approaches based on dynamical Lie algebras characterize the reachable orbit generated by a variational ansatz and provide important information about controllability and expressivity. However, optimization is inherently a local differential process, and the geometric mechanisms governing the transmission of optimization information remain poorly understood. In this work, we develop a differential-geometric framework for trainability based on the variational Jacobian. The Jacobian is interpreted as the differential map connecting the parameter manifold with the tangent space of the reachable orbit. \textcolor{blue}{We derive an exact modal decomposition of gradient generation in terms of Jacobian singular directions and task-dependent modal information, showing that gradient suppression may arise from spectral attenuation, from a reduction of the task-gradient magnitude, from directional misalignment between the task gradient and the Jacobian-accessible subspace, or from combinations of these effects.} We further establish an explicit connection between the variational Jacobian and the underlying dynamical Lie algebra through effective commutator directions. \textcolor{blue}{In the numerical settings considered here, coarse task-independent spectral diagnostics such as the Jacobian rank, the largest singular value, and the total spectral weight exhibit little correlation with optimization performance, whereas normalized directional alignment and task-weighted spectral transmission retain significant predictive associations.} \textcolor{blue}{Finally, we show that Jacobian degeneration suppresses the task-Hessian component transmitted through the variational map, while the additional second-order map contribution need not vanish.} \textcolor{blue}{Taken together, these results provide a geometric framework in which local trainability can be viewed as emerging from the interaction between Lie-algebraic structure, Jacobian geometry, and the learning task, and as a problem of differential information transmission rather than accessibility alone.}

DOI
10.1088/2058-9565/aebe5d

Related papers

Lie-theoretic structure of parameter gradients in variational quantum circuits

María-Luisa Pérez-Delgado, Roberto Casado Vara

Abstract Variational quantum circuits are a central paradigm of quantum machine learning and near-term quantum computing, yet their practical optimization is often limited by strongly suppressed parameter gradients. Dynamical Lie algebras provide a rigorous description of the infinitesimal directions accessible to a variational architecture, but dynamical accessibility alone does not determine the gradient signal exposed by an actual circuit parametrization. In this work, we develop a Lie-theoretic description of parameter-gradient structure that separates four successive mechanisms: dynamical accessibility, observable visibility, state-dependent activation, and local parameter realization. The optimization observable determines which accessible directions can influence the objective and how strongly they couple to it, while the quantum state selects which of these response modes are locally activated. This information is then pulled back through the circuit parametrization to recover the actual parameter gradients. The resulting construction yields an exact modal decomposition of the accessible gradient signal, a hierarchy of structural bounds, and a natural description of state averaging. An analytical single-qubit example and controlled numerical experiments validate the successive levels of the hierarchy and show that accessible Lie dimension alone is insufficient to characterize the parameter-gradient scale. The results support a mechanism-based view of variational trainability in which parameter gradients emerge from the interaction between accessible dynamics, observable coupling, quantum-state activation, and circuit parametrization.

Quantum Science and Technology•Oct 13, 2026•0 citations

Circuit Synthesis for Variational Quantum Algorithms: The Depth of Algebra and Geometry

Boris Tsvelikhovskiy

The analysis of Hamiltonian Variational Ansätze centers on three fundamental questions: which states are exactly reachable from a given initial state, what native control depth suffices for local and global synthesis, and whether a bounded circuit extension can expose a direction of decreasing cost at a suboptimal output. We address these challenges by leveraging the dynamical Lie algebras (DLAs) associated with the circuits and the geometry of the initial state's orbit under the action of the corresponding dynamical Lie group $G$. We show that an initial state has a closed projective orbit whenever it is a nondegenerate eigenstate of a control Hamiltonian. Combined with asymptotic QAOA convergence, this guarantees exact, finite depth ground state preparation for architectures employing diagonal problem Hamiltonians and irreducible stoquastic mixers. We bound the number of native control exponentials required for local unitary synthesis and state preparation using DLA commutator filtration growth alongside reachable orbit dimensions. Complementing these local results, we construct global frameworks on invariant sectors equipped with full unitary or special unitary dynamical Lie algebras. These constructions yield explicit applications to Pauli-generated systems and constrained maximum independent set multi-angle QAOA circuits; specifically, we show that their native control costs are directly determined by commutator filtration depth and independent-set toggle-group geometry, respectively. Finally, if the dynamical Lie group is compact, the observable $H_P$ generates an admissible evolution ($iH_P \in \mathfrak{g}$, where $\mathfrak{g}$ is the DLA), and the projective orbit of the initial state contains a ground state ray of $H_P$, then a bounded depth, identity-initialized circuit extension exhibits either first-order descent or negative curvature at every suboptimal circuit output.

quant-pharXiv:2610.22689•Oct 19, 2026•0 citations

Scaling Behavior of Parameterized Quantum Circuits from a Lie-Algebraic Perspective

Hiroshi Ohno

Understanding how the performance of parameterized quantum circuits scales with available resources is important for characterizing their trainability and effective model capacity. In this study, we numerically investigate data scaling, model scaling, and compute scaling in parameterized quantum circuits and examine Lie-algebraic quantities as alternative measures of model size. In addition to the number of circuit parameters, we consider the dimension of the dynamical Lie algebra, the observable-orbit dimension, and a Jacobian effective dimension defined as the rank of the Jacobian of the parameterized observable orbit. Using a regression task with randomly generated Pauli-string generators, we observe decreasing loss with increasing training dataset size, parameter size, and number of optimization iterations over the ranges investigated. For model scaling, the dynamical Lie algebra and observable orbit dimensions rapidly saturate as the parameter size increases, whereas the Jacobian effective dimension remains strongly correlated with the parameter size and exhibits comparable scaling behavior. These results suggest that the Jacobian effective dimension provides a geometry-aware measure of the locally accessible observable degrees of freedom of finite-depth parameterized quantum circuits and may serve as a useful scaling parameter beyond the nominal parameter size.

quant-pharXiv:2608.20603•Aug 24, 2026•0 citations

Characterizing privacy in quantum machine learning

Jamie Heredge, Niraj Kumar, Dylan Herman +5 more

Abstract Ensuring data privacy in machine learning models is critical, especially in distributed settings where model gradients are shared among multiple parties for collaborative learning. Motivated by the increasing success of recovering input data from the gradients of classical models, this study investigates the analogous challenge for variational quantum circuits (VQC) as quantum machine learning models. We highlight the crucial role of the dynamical Lie algebra (DLA) in determining privacy vulnerabilities. While the DLA has been linked to the trainability and simulatability of VQC models, we establish its connection to privacy for the first time. We show that properties conducive to VQC trainability, such as a polynomial-sized DLA, also facilitate extracting detailed snapshots of the input, posing a weak privacy breach. We further investigate conditions for a strong privacy breach, where original input data can be recovered from snapshots by classical or quantum-assisted methods. We establish properties of the encoding map, such as classical simulatability, overlap with DLA basis, and its Fourier frequency characteristics that enable such a privacy breach of VQC models. Our framework thus guides the design of quantum machine learning models, balancing trainability and robust privacy protection.

arXiv:2405.08801•npj Quantum Information•May 19, 2025•17 citations

Beyond the Expressivity-Trainability Paradox: A Dynamical Lie Algebra Perspective on Navigating Barren Plateaus in Quantum Machine Learning

Kung-Ming Lan, Edward Huang

As Quantum Machine Learning (QML) transitions toward practical implementation, the field faces a critical architectural bottleneck that challenges the fundamental assumptions of classical statistical learning theory. In classical deep learning, increasing model capacity typically risks overfitting. However, this study advances a counter-intuitive paradigm: unstructured contemporary QML architectures suffer from a profound state of quantum underfitting, driven by the "expressivity-trainability paradox." We demonstrate that the vast Hilbert space capacity of Parameterized Quantum Circuits (PQCs)-traditionally chased as the source of quantum advantage is the direct mathematical cause of Barren Plateaus (BPs), where gradient landscapes become exponentially flat. By synthesizing recent breakthroughs in Dynamical Lie Algebras (DLAs) and Geometric QML, we establish a comprehensive framework linking the algebraic dimension of circuit generators to their optimization dynamics. Furthermore, we empirically validate this framework on a non-linear binary classification task, illuminating a uniquely quantum manifestation of the bias-variance tradeoff: while unstructured architectures achieve near-perfect training accuracy via unscalable parameterization (quantum overfitting), embedding group-theoretic geometric priors acts as a structural regularizer. By restricting the DLA growth to a polynomial regime, our symmetry-preserving approach sacrifices raw memorization capacity to guarantee scalable, gradient-rich training landscapes, offering a robust roadmap for "Trainability-by-Design" in scalable quantum neural networks.

cs.LGCross-listedarXiv:2606.31536•Jul 1, 2026•1 citation

TensorDual-VQC: Operator Learning for Scalable and Noise-Robust Variational Quantum Circuits

Jun Qi, Chao-Han Huck Yang, Pooja Rao +2 more

Abstract Variational quantum circuits (VQCs) are a central paradigm for quantum machine learning, yet their practical deployment is limited by poor trainability, sensitivity to noise, and the lack of input-adaptive parameterization. In this work, we introduce TensorDual-VQC, a tensor-structured operator-learning framework that models variational quantum computation as an input-conditioned mapping that jointly governs quantum state encoding and circuit parameter generation. The proposed approach employs a shared low-rank Tensor-Train (TT) backbone with dual output heads, inducing a coupled representation that constrains the hypothesis space to a structured low-dimensional manifold. Under standard smoothness and low-rank assumptions, we show that the approximation behavior is governed by the TT-rank rather than the ambient parameter dimension, and that shared latent structure can enable more compact representations than decoupled parameterizations in structured regimes. We further analyze trainability through the induced Neural Tangent Kernel, showing that the multi-branch gradient structure enriches the span of gradient features and can improve kernel conditioning under mild non-degeneracy conditions. In addition, we relate robustness to quantum noise to the intrinsic effective dimension of the tensor parameter manifold, providing a first-order scaling characterization of output variance under stochastic perturbations. We evaluate TensorDual-VQC on quantum dot classification, quantum simulation, and combinatorial optimization tasks under both simulated noise and real quantum hardware. Across all settings, the proposed framework achieves higher accuracy, faster convergence, and greater stability than standard VQCs and hypernetwork-based baselines when quantum resources are matched. These results suggest that structured operator learning with shared low-rank representations provides a principled and practical approach to scalable, noise-resilient quantum learning in the NISQ regime.

•May 15, 2026•0 citations
Abstract Understanding the origins of trainability in variational quantum circuits remains one of the central challenges in quantum machine learning. Existing approaches based on dynamical Lie algebras characterize the reachable orbit generated by a variational ansatz and provide important information about controllability and expressivity. However, optimization is inherently a local differential process, and the geometric mechanisms governing the transmission of optimization information remain poorly understood. In this work, we develop a differential-geometric framework for trainability based on the variational Jacobian. The Jacobian is interpreted as the differential map connecting the parameter manifold with the tangent space of the reachable orbit. \textcolor{blue}{We derive an exact modal decomposition of gradient generation in terms of Jacobian singular directions and task-dependent modal information, showing that gradient suppression may arise from spectral attenuation, from a reduction of the task-gradient magnitude, from directional misalignment between the task gradient and the Jacobian-accessible subspace, or from combinations of these effects.} We further establish an explicit connection between the variational Jacobian and the underlying dynamical Lie algebra through effective commutator directions. \textcolor{blue}{In the numerical settings considered here, coarse task-independent spectral diagnostics such as the Jacobian rank, the largest singular value, and the total spectral weight exhibit little correlation with optimization performance, whereas normalized directional alignment and task-weighted spectral transmission retain significant predictive associations.} \textcolor{blue}{Finally, we show that Jacobian degeneration suppresses the task-Hessian component transmitted through the variational map, while the additional second-order map contribution need not vanish.} \textcolor{blue}{Taken together, these results provide a geometric framework in which local trainability can be viewed as emerging from the interaction between Lie-algebraic structure, Jacobian geometry, and the learning task, and as a problem of differential information transmission rather than accessibility alone.}
Abstract Variational quantum circuits are a central paradigm of quantum machine learning and near-term quantum computing, yet their practical optimization is often limited by strongly suppressed parameter gradients. Dynamical Lie algebras provide a rigorous description of the infinitesimal directions accessible to a variational architecture, but dynamical accessibility alone does not determine the gradient signal exposed by an actual circuit parametrization. In this work, we develop a Lie-theoretic description of parameter-gradient structure that separates four successive mechanisms: dynamical accessibility, observable visibility, state-dependent activation, and local parameter realization. The optimization observable determines which accessible directions can influence the objective and how strongly they couple to it, while the quantum state selects which of these response modes are locally activated. This information is then pulled back through the circuit parametrization to recover the actual parameter gradients. The resulting construction yields an exact modal decomposition of the accessible gradient signal, a hierarchy of structural bounds, and a natural description of state averaging. An analytical single-qubit example and controlled numerical experiments validate the successive levels of the hierarchy and show that accessible Lie dimension alone is insufficient to characterize the parameter-gradient scale. The results support a mechanism-based view of variational trainability in which parameter gradients emerge from the interaction between accessible dynamics, observable coupling, quantum-state activation, and circuit parametrization.
The analysis of Hamiltonian Variational Ansätze centers on three fundamental questions: which states are exactly reachable from a given initial state, what native control depth suffices for local and global synthesis, and whether a bounded circuit extension can expose a direction of decreasing cost at a suboptimal output. We address these challenges by leveraging the dynamical Lie algebras (DLAs) associated with the circuits and the geometry of the initial state's orbit under the action of the corresponding dynamical Lie group GGG. We show that an initial state has a closed projective orbit whenever it is a nondegenerate eigenstate of a control Hamiltonian. Combined with asymptotic QAOA convergence, this guarantees exact, finite depth ground state preparation for architectures employing diagonal problem Hamiltonians and irreducible stoquastic mixers. We bound the number of native control exponentials required for local unitary synthesis and state preparation using DLA commutator filtration growth alongside reachable orbit dimensions. Complementing these local results, we construct global frameworks on invariant sectors equipped with full unitary or special unitary dynamical Lie algebras. These constructions yield explicit applications to Pauli-generated systems and constrained maximum independent set multi-angle QAOA circuits; specifically, we show that their native control costs are directly determined by commutator filtration depth and independent-set toggle-group geometry, respectively. Finally, if the dynamical Lie group is compact, the observable HPH_PHP​ generates an admissible evolution (iHP∈giH_P \in \mathfrak{g}iHP​∈g, where g\mathfrak{g}g is the DLA), and the projective orbit of the initial state contains a ground state ray of HPH_PHP​, then a bounded depth, identity-initialized circuit extension exhibits either first-order descent or negative curvature at every suboptimal circuit output.
Understanding how the performance of parameterized quantum circuits scales with available resources is important for characterizing their trainability and effective model capacity. In this study, we numerically investigate data scaling, model scaling, and compute scaling in parameterized quantum circuits and examine Lie-algebraic quantities as alternative measures of model size. In addition to the number of circuit parameters, we consider the dimension of the dynamical Lie algebra, the observable-orbit dimension, and a Jacobian effective dimension defined as the rank of the Jacobian of the parameterized observable orbit. Using a regression task with randomly generated Pauli-string generators, we observe decreasing loss with increasing training dataset size, parameter size, and number of optimization iterations over the ranges investigated. For model scaling, the dynamical Lie algebra and observable orbit dimensions rapidly saturate as the parameter size increases, whereas the Jacobian effective dimension remains strongly correlated with the parameter size and exhibits comparable scaling behavior. These results suggest that the Jacobian effective dimension provides a geometry-aware measure of the locally accessible observable degrees of freedom of finite-depth parameterized quantum circuits and may serve as a useful scaling parameter beyond the nominal parameter size.
Abstract Ensuring data privacy in machine learning models is critical, especially in distributed settings where model gradients are shared among multiple parties for collaborative learning. Motivated by the increasing success of recovering input data from the gradients of classical models, this study investigates the analogous challenge for variational quantum circuits (VQC) as quantum machine learning models. We highlight the crucial role of the dynamical Lie algebra (DLA) in determining privacy vulnerabilities. While the DLA has been linked to the trainability and simulatability of VQC models, we establish its connection to privacy for the first time. We show that properties conducive to VQC trainability, such as a polynomial-sized DLA, also facilitate extracting detailed snapshots of the input, posing a weak privacy breach. We further investigate conditions for a strong privacy breach, where original input data can be recovered from snapshots by classical or quantum-assisted methods. We establish properties of the encoding map, such as classical simulatability, overlap with DLA basis, and its Fourier frequency characteristics that enable such a privacy breach of VQC models. Our framework thus guides the design of quantum machine learning models, balancing trainability and robust privacy protection.
As Quantum Machine Learning (QML) transitions toward practical implementation, the field faces a critical architectural bottleneck that challenges the fundamental assumptions of classical statistical learning theory. In classical deep learning, increasing model capacity typically risks overfitting. However, this study advances a counter-intuitive paradigm: unstructured contemporary QML architectures suffer from a profound state of quantum underfitting, driven by the "expressivity-trainability paradox." We demonstrate that the vast Hilbert space capacity of Parameterized Quantum Circuits (PQCs)-traditionally chased as the source of quantum advantage is the direct mathematical cause of Barren Plateaus (BPs), where gradient landscapes become exponentially flat. By synthesizing recent breakthroughs in Dynamical Lie Algebras (DLAs) and Geometric QML, we establish a comprehensive framework linking the algebraic dimension of circuit generators to their optimization dynamics. Furthermore, we empirically validate this framework on a non-linear binary classification task, illuminating a uniquely quantum manifestation of the bias-variance tradeoff: while unstructured architectures achieve near-perfect training accuracy via unscalable parameterization (quantum overfitting), embedding group-theoretic geometric priors acts as a structural regularizer. By restricting the DLA growth to a polynomial regime, our symmetry-preserving approach sacrifices raw memorization capacity to guarantee scalable, gradient-rich training landscapes, offering a robust roadmap for "Trainability-by-Design" in scalable quantum neural networks.
Abstract Variational quantum circuits (VQCs) are a central paradigm for quantum machine learning, yet their practical deployment is limited by poor trainability, sensitivity to noise, and the lack of input-adaptive parameterization. In this work, we introduce TensorDual-VQC, a tensor-structured operator-learning framework that models variational quantum computation as an input-conditioned mapping that jointly governs quantum state encoding and circuit parameter generation. The proposed approach employs a shared low-rank Tensor-Train (TT) backbone with dual output heads, inducing a coupled representation that constrains the hypothesis space to a structured low-dimensional manifold. Under standard smoothness and low-rank assumptions, we show that the approximation behavior is governed by the TT-rank rather than the ambient parameter dimension, and that shared latent structure can enable more compact representations than decoupled parameterizations in structured regimes. We further analyze trainability through the induced Neural Tangent Kernel, showing that the multi-branch gradient structure enriches the span of gradient features and can improve kernel conditioning under mild non-degeneracy conditions. In addition, we relate robustness to quantum noise to the intrinsic effective dimension of the tensor parameter manifold, providing a first-order scaling characterization of output variance under stochastic perturbations. We evaluate TensorDual-VQC on quantum dot classification, quantum simulation, and combinatorial optimization tasks under both simulated noise and real quantum hardware. Across all settings, the proposed framework achieves higher accuracy, faster convergence, and greater stability than standard VQCs and hypernetwork-based baselines when quantum resources are matched. These results suggest that structured operator learning with shared low-rank representations provides a principled and practical approach to scalable, noise-resilient quantum learning in the NISQ regime.