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:2512.09469

LiePrune: Lie Group and Quantum Geometric Dual Representation for One-Shot Structured Pruning of Quantum Neural Networks

Haijian Shao, Bowen Yang, Wei Liu, Xing Deng, Yingtao Jiang

quant-phcs.CVSubmitted Dec 10, 2025• Announced Dec 11, 2025• 1 citation
arXivHTMLPDF

Abstract

Quantum neural networks (QNNs) and parameterized quantum circuits (PQCs) are key building blocks for near-term quantum machine learning. However, their scalability is constrained by excessive parameters, barren plateaus, and hardware limitations. We propose LiePrune, the first mathematically grounded one-shot structured pruning framework for QNNs that leverages Lie group structure and quantum geometric information. Each gate is jointly represented in a Lie group--Lie algebra dual space and a quantum geometric feature space, enabling principled redundancy detection and aggressive compression. Experiments on quantum classification (MNIST, FashionMNIST), quantum generative modeling (Bars-and-Stripes), and quantum chemistry (LiH VQE) show that LiePrune achieves over $10\times$ compression with negligible or even improved task performance, while providing provable guarantees on redundancy detection, functional approximation, and computational complexity.

Comments
7 pages, 2 figures

Related papers

One-Shot Structured Pruning of Quantum Neural Networks via $q$-Group Engineering and Quantum Geometric Metrics

Haijian Shao, Wei Liu, Xing Deng +1 more

Quantum neural networks (QNNs) suffer from severe gate-level redundancy, which hinders their deployment on noisy intermediate-scale quantum (NISQ) devices. In this work, we propose q-iPrune, a one-shot structured pruning framework grounded in the algebraic structure of $q$-deformed groups and task-conditioned quantum geometry. Unlike prior heuristic or gradient-based pruning methods, q-iPrune formulates redundancy directly at the gate level. Each gate is compared within an algebraically consistent subgroup using a task-conditioned $q$-overlap distance, which measures functional similarity through state overlaps on a task-relevant ensemble. A gate is removed only when its replacement by a subgroup representative provably induces a bounded deviation on all task observables. We establish three rigorous theoretical guarantees. First, we prove completeness of redundancy pruning: no gate that violates the prescribed similarity threshold is removed. Second, we show that the pruned circuit is functionally equivalent up to an explicit, task-conditioned error bound, with a closed-form dependence on the redundancy tolerance and the number of replaced gates. Third, we prove that the pruning procedure is computationally feasible, requiring only polynomial-time comparisons and avoiding exponential enumeration over the Hilbert space. To adapt pruning decisions to hardware imperfections, we introduce a noise-calibrated deformation parameter $λ$ that modulates the $q$-geometry and redundancy tolerance. Experiments on standard quantum machine learning benchmarks demonstrate that q-iPrune achieves substantial gate reduction while maintaining bounded task performance degradation, consistent with our theoretical guarantees.

quant-pharXiv:2512.24019•Dec 31, 2025•0 citations

LieTrunc-QNN: Lie Algebra Truncation and Quantum Expressivity Phase Transition from LiePrune to Provably Stable Quantum Neural Networks

Haijian Shao, Dalong A. Zhao, Xing Deng +2 more

Quantum Machine Learning (QML) is fundamentally limited by two challenges: barren plateaus (exponentially vanishing gradients) and the fragility of parameterized quantum circuits under noise. Despite extensive empirical studies, a unified theoretical framework remains lacking. We introduce LieTrunc-QNN, an algebraic-geometric framework that characterizes trainability via Lie-generated dynamics. Parameterized quantum circuits are modeled as Lie subalgebras of u(2^n), whose action induces a Riemannian manifold of reachable quantum states. Expressivity is reinterpreted as intrinsic manifold dimension and geometry. We establish a geometric capacity-plateau principle: increasing effective dimension leads to exponential gradient suppression due to concentration of measure. By restricting to structured Lie subalgebras (LieTrunc), the manifold is contracted, preventing concentration and preserving non-degenerate gradients. We prove two main results: (1) a trainability lower bound for LieTrunc-QNN, and (2) that the Fubini-Study metric rank is bounded by the algebraic span of generators, showing expressivity is governed by structure rather than parameter count. Compact Lie subalgebras also provide inherent robustness to perturbations. Importantly, we establish a polynomial trainability regime where gradient variance decays polynomially instead of exponentially. Experiments (n=2-6) validate the theory: LieTrunc-QNN maintains stable gradients and high effective dimension, while random truncation leads to metric rank collapse. At n=6, full metric rank is preserved (rank=16). Results support a scaling law between gradient variance and effective dimension. This work provides a unified geometric framework for QNN design, linking Lie algebra, manifold geometry, and optimization.

arXiv:2604.02697•Apr 3, 2026•0 citations

Geometric Optimization on Lie Groups: A Lie-Theoretic Explanation of Barren Plateau Mitigation for Variational Quantum Algorithms

Zhehao Yi, Rahul Bhadani

Barren plateaus, which means the training gradients become extremely small, pose a major challenge in optimizing parameterized quantum circuits, often making the learning process impractically slow or stall. This work shows why using neural networks to generate quantum circuit parameters helps overcome this difficulty. We introduce a geometric viewpoint that describes how the parameters produced by neural networks evolve during training. Our analysis shows that these parameters follow smooth and efficient paths that avoid the flat regions in the training that cause barren plateaus. This provides a computational explanation for the improved trainability observed in recent neural network-assisted quantum learning methods. Overall, our findings bridge ideas from quantum machine learning and computational optimization, offering new insight into the structure of quantum models and guiding future approaches for designing more trainable quantum circuits or parameter initialization.

quant-pharXiv:2512.02078•Dec 2, 2025•0 citations

Lie-geometric trainability of quantum dynamical systems: avoiding barren plateaus via low-dimensional Lie subalgebras

Haijian Shao, Yujie Wu, Xing Deng +1 more

Abstract We present a Lie-geometric framework for analyzing the trainability of quantum neural networks (QNNs) through the algebraic structure of their generator spaces. We prove that QNNs whose dynamics are restricted to polynomial-dimensional Lie subalgebras of su ( 2 n ) admit a polynomial lower bound on gradient variance, thereby avoiding barren plateaus by construction. In contrast, architectures exploring the full Lie algebra su ( 2 n ) exhibit exponentially vanishing gradient variance, O ( 2 − n ) , due to the exponential growth of the associated unitary orbit dimensions. Our results interpret barren plateaus as a geometric concentration phenomenon arising from high-dimensional Lie-group actions, rather than as an intrinsic limitation of parameterized quantum models. We further illustrate the mechanism using a finite-size collective-spin benchmark and a minimal two-qubit sanity check, both of which are consistent with the theoretical predictions.

Physica Scripta•Jun 15, 2026•1 citation

Exact Algebraic Reduction of Quantum Neural Circuits: Observable-Dependent Renormalization and Curvature-Based Reliability Control

Isamu Ohnishi, Chavis Srichan

This conference presentation introduces an algebraic framework for the exact reduction of quantum neural circuits through observable-dependent renormalization and geometric reliability control. The proposed approach addresses fundamental challenges in quantum machine learning, including circuit complexity, fragmented mathematical representations, training stability, and the reliability of generative models. The framework represents parameterized quantum circuits as quantum dynamical semigroups and constructs an observable-dependent symmetry subalgebra using dynamical Lie algebra closure. This construction enables the derivation of reduced effective models that preserve designated observables exactly while maintaining complete positivity and trace preservation. The presentation further investigates the geometric structure of reduced quantum models through quantum Fisher information, Berry curvature, and context-dependent attention metrics. Geometric regularization is proposed to improve training stability and address barren plateaus, while curvature-based reliability monitoring provides a mathematical approach to detecting deviations of generated outputs from learned data manifolds. The proposed methodology offers potential applications in resource-efficient quantum machine learning, hybrid quantum-classical computing, model robustness, and AI reliability. Future research directions include hardware-aware algebraic reduction, continuous-variable quantum systems, and curvature-based monitoring for trustworthy artificial intelligence.

•Nov 1, 2026•0 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•0 citations
Quantum neural networks (QNNs) and parameterized quantum circuits (PQCs) are key building blocks for near-term quantum machine learning. However, their scalability is constrained by excessive parameters, barren plateaus, and hardware limitations. We propose LiePrune, the first mathematically grounded one-shot structured pruning framework for QNNs that leverages Lie group structure and quantum geometric information. Each gate is jointly represented in a Lie group--Lie algebra dual space and a quantum geometric feature space, enabling principled redundancy detection and aggressive compression. Experiments on quantum classification (MNIST, FashionMNIST), quantum generative modeling (Bars-and-Stripes), and quantum chemistry (LiH VQE) show that LiePrune achieves over 10×10\times10× compression with negligible or even improved task performance, while providing provable guarantees on redundancy detection, functional approximation, and computational complexity.
One-Shot Structured Pruning of Quantum Neural Networks via qqq-Group Engineering and Quantum Geometric Metrics
Quantum neural networks (QNNs) suffer from severe gate-level redundancy, which hinders their deployment on noisy intermediate-scale quantum (NISQ) devices. In this work, we propose q-iPrune, a one-shot structured pruning framework grounded in the algebraic structure of qqq-deformed groups and task-conditioned quantum geometry. Unlike prior heuristic or gradient-based pruning methods, q-iPrune formulates redundancy directly at the gate level. Each gate is compared within an algebraically consistent subgroup using a task-conditioned qqq-overlap distance, which measures functional similarity through state overlaps on a task-relevant ensemble. A gate is removed only when its replacement by a subgroup representative provably induces a bounded deviation on all task observables. We establish three rigorous theoretical guarantees. First, we prove completeness of redundancy pruning: no gate that violates the prescribed similarity threshold is removed. Second, we show that the pruned circuit is functionally equivalent up to an explicit, task-conditioned error bound, with a closed-form dependence on the redundancy tolerance and the number of replaced gates. Third, we prove that the pruning procedure is computationally feasible, requiring only polynomial-time comparisons and avoiding exponential enumeration over the Hilbert space. To adapt pruning decisions to hardware imperfections, we introduce a noise-calibrated deformation parameter λλλ that modulates the qqq-geometry and redundancy tolerance. Experiments on standard quantum machine learning benchmarks demonstrate that q-iPrune achieves substantial gate reduction while maintaining bounded task performance degradation, consistent with our theoretical guarantees.
Quantum Machine Learning (QML) is fundamentally limited by two challenges: barren plateaus (exponentially vanishing gradients) and the fragility of parameterized quantum circuits under noise. Despite extensive empirical studies, a unified theoretical framework remains lacking. We introduce LieTrunc-QNN, an algebraic-geometric framework that characterizes trainability via Lie-generated dynamics. Parameterized quantum circuits are modeled as Lie subalgebras of u(2^n), whose action induces a Riemannian manifold of reachable quantum states. Expressivity is reinterpreted as intrinsic manifold dimension and geometry. We establish a geometric capacity-plateau principle: increasing effective dimension leads to exponential gradient suppression due to concentration of measure. By restricting to structured Lie subalgebras (LieTrunc), the manifold is contracted, preventing concentration and preserving non-degenerate gradients. We prove two main results: (1) a trainability lower bound for LieTrunc-QNN, and (2) that the Fubini-Study metric rank is bounded by the algebraic span of generators, showing expressivity is governed by structure rather than parameter count. Compact Lie subalgebras also provide inherent robustness to perturbations. Importantly, we establish a polynomial trainability regime where gradient variance decays polynomially instead of exponentially. Experiments (n=2-6) validate the theory: LieTrunc-QNN maintains stable gradients and high effective dimension, while random truncation leads to metric rank collapse. At n=6, full metric rank is preserved (rank=16). Results support a scaling law between gradient variance and effective dimension. This work provides a unified geometric framework for QNN design, linking Lie algebra, manifold geometry, and optimization.
Barren plateaus, which means the training gradients become extremely small, pose a major challenge in optimizing parameterized quantum circuits, often making the learning process impractically slow or stall. This work shows why using neural networks to generate quantum circuit parameters helps overcome this difficulty. We introduce a geometric viewpoint that describes how the parameters produced by neural networks evolve during training. Our analysis shows that these parameters follow smooth and efficient paths that avoid the flat regions in the training that cause barren plateaus. This provides a computational explanation for the improved trainability observed in recent neural network-assisted quantum learning methods. Overall, our findings bridge ideas from quantum machine learning and computational optimization, offering new insight into the structure of quantum models and guiding future approaches for designing more trainable quantum circuits or parameter initialization.
Abstract We present a Lie-geometric framework for analyzing the trainability of quantum neural networks (QNNs) through the algebraic structure of their generator spaces. We prove that QNNs whose dynamics are restricted to polynomial-dimensional Lie subalgebras of su ( 2 n ) admit a polynomial lower bound on gradient variance, thereby avoiding barren plateaus by construction. In contrast, architectures exploring the full Lie algebra su ( 2 n ) exhibit exponentially vanishing gradient variance, O ( 2 − n ) , due to the exponential growth of the associated unitary orbit dimensions. Our results interpret barren plateaus as a geometric concentration phenomenon arising from high-dimensional Lie-group actions, rather than as an intrinsic limitation of parameterized quantum models. We further illustrate the mechanism using a finite-size collective-spin benchmark and a minimal two-qubit sanity check, both of which are consistent with the theoretical predictions.
This conference presentation introduces an algebraic framework for the exact reduction of quantum neural circuits through observable-dependent renormalization and geometric reliability control. The proposed approach addresses fundamental challenges in quantum machine learning, including circuit complexity, fragmented mathematical representations, training stability, and the reliability of generative models. The framework represents parameterized quantum circuits as quantum dynamical semigroups and constructs an observable-dependent symmetry subalgebra using dynamical Lie algebra closure. This construction enables the derivation of reduced effective models that preserve designated observables exactly while maintaining complete positivity and trace preservation. The presentation further investigates the geometric structure of reduced quantum models through quantum Fisher information, Berry curvature, and context-dependent attention metrics. Geometric regularization is proposed to improve training stability and address barren plateaus, while curvature-based reliability monitoring provides a mathematical approach to detecting deviations of generated outputs from learned data manifolds. The proposed methodology offers potential applications in resource-efficient quantum machine learning, hybrid quantum-classical computing, model robustness, and AI reliability. Future research directions include hardware-aware algebraic reduction, continuous-variable quantum systems, and curvature-based monitoring for trustworthy artificial intelligence.
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.