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

Haijian Shao; Dalong Zhao; Xing Deng; Wenzheng Zhu; Yingtao Jiang

cs.LGApr 3, 2026

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

Authors: Haijian Shao, Dalong Zhao, Xing Deng, Wenzheng Zhu, Yingtao Jiang

Organizations: School of Computer, Jiangsu University of Science and Technology, Zhenjiang 212003, China · Department of Electrical and Computer Engineering, University of Nevada, Las Vegas, USA

Abstract

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.

Figures & tables

\mathfrak{g}_{\text{circ}}\xrightarrow{\text{Lie reduction}}\mathfrak{g}_{\text{trunc}}\;\Longleftrightarrow\;\mathcal{M}\xrightarrow{\text{manifold contraction}}\mathcal{M}_{\text{trunc}}\;\Longleftrightarrow\;T\mathcal{M}\xrightarrow{\text{tangent reduction}}T\mathcal{M}_{\text{trunc}}

Table 1

Method	$d_{\mathrm{eff}}$	$\mathrm{rank}(G)$	Gradient Variance
Full	12.41	16	$2.00\times 10^{0}$
RandomTrunc	1.99	2	$2.75\times 10^{-1}$
LieTrunc	13.36	16	$1.16\times 10^{0}$

Table 1: Geometric properties for

n=6

qubits.

Figure 1: Left: gradient variance vs. qubit number; middle: effective dimension $d_{\text{eff}}$ ; right: variance–effective dimension product. LieTrunc stabilizes gradients while preserving expressivity.

Figure 2: Fubini–Study metric eigenvalue spectra across architectures. RandomTrunc shows spectral collapse; LieTrunc maintains full structure.

Figure 3: Task loss across qubit counts. LieTrunc-QNN achieves stable, competitive performance.

Figure 4: Fubini–Study metric spectrum at $n=6$ . RandomTrunc collapses; LieTrunc remains full-rank.

Explore similar work

Jun 30, 2026

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

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.

Kung-Ming Lan, Edward Huang

Department of Industrial Engineering and Enterprise Information, Tunghai University, Taichung 40704, Taiwan · Department of Industrial and Systems Engineering, 3306 Shelby Center, Auburn University, Auburn, AL, USA

Quantum Machine Learning Barren Plateaus Variational Quantum Circuits Quantum Neural Networks

Ask PDF

Sep 25, 2026

Modeling quantum neural network gradient with reinforcement learning

Training quantum neural networks (QNNs) on near-term hardware remains hampered by two compounding difficulties: the exponential vanishing of gradient variance known as the barren plateau, and the

\mathcal{O}(L \cdot 2^n)

time and memory cost of differentiating through an

n

-qubit,

L

-layer circuit. We propose RLQ-Grad, a reinforcement-learning-based optimizer in which a classical policy

π_φ

(a spectrally-normalized PPO agent) learns to propose parameter updates directly, conditioned on the QNN's current parameters, loss, accuracy, and previous update. Because the surrogate gradient is emitted by a classical network rather than obtained by differentiating through the unitary

U(θ)

, its variance is not constrained by the barren plateau concentration bound, and its cost scales with the number of trainable parameters rather than the Hilbert-space dimension. We prove these properties formally and verify them on a hardware-efficient ansatz across four supervised benchmarks with up to

n=20

qubits. RLQ-Grad preserves a near-flat gradient-variance curve where backpropagation, parameter-shift, and adjoint differentiation decay by 1 to 2 orders of magnitude. Accounting for the full training pipeline (PPO rollouts, actor-critic updates, and optimizer states), RLQ-Grad needs under 2 MB of memory and runs

2490\times

7876\times

, and

673\times

faster per iteration than these three methods at

n=20

. It improves top-1 accuracy by up to

+10\%

over gradient-based baselines on circuits of up to 12 qubits, and matches dedicated barren plateau mitigation methods on CIFAR-10 at 14 to 20 qubits, where evolutionary and gradient-free optimizers collapse to chance.

Nhan Trong Luu, Duong Trung Luu, Nam Ngoc Pham +1

College of Information and Communication Technology, Can Tho University, Can Tho, Vietnam · College of Engineering and Computer Science, VinUniversity, Hanoi, Vietnam · Center for Digital Transformation and Communications, Can Tho University, Can Tho, Vietnam +1

Quantum Neural Networks Quantum Circuit Trainability Hybrid Quantum-Classical ML Barren Plateaus

Ask PDF

Mar 3, 2026

From Reachability to Learnability: Geometric Design Principles for Quantum Neural Networks

Classical deep networks are effective because depth enables adaptive geometric deformation of data representations. In quantum neural networks (QNNs), however, depth or state reachability alone does not guarantee this feature-learning capability. We study this question in the pure-state setting by viewing encoded data as an embedded manifold in

\mathbb{C}P^{2^n-1}

and analysing infinitesimal unitary actions through Lie-algebra directions. We introduce Classical-to-Lie-algebra (CLA) maps and the criterion of almost Complete Local Selectivity (aCLS), which combines directional completeness with data-dependent local selectivity. Within this framework, we show that data-independent trainable unitaries are complete but non-selective, i.e. learnable rigid reorientations, whereas pure data encodings are selective but non-tunable, i.e. fixed deformations. Hence, geometric flexibility requires a non-trivial joint dependence on data and trainable weights. We further show that accessing high-dimensional deformations of many-qubit state manifolds requires parametrised entangling directions; fixed entanglers such as CNOT alone do not provide adaptive geometric control. Numerical examples validate that aCLS-satisfying data re-uploading models outperform non-tunable schemes while requiring only a quarter of the gate operations. Thus, the resulting picture reframes QNN design from state reachability to controllable geometry of hidden quantum representations.

Vishal S. Ngairangbam, Michael Spannowsky

Institute for Particle Physics Phenomenology, Department of Physics Durham University, Durham DH1 3LE, United Kingdom · Institute for Theoretical Physics, Karlsruhe Institute of Technology (KIT), Wolfgang-Gaede-Str. 1, 76131 Karlsruhe, Germany

Quantum Neural Networks Quantum Machine Learning Quantum Feature Maps Quantum Circuit Trainability

Ask PDF