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

• URL: http://arxiv.org/abs/2606.31536v3
• Date: Thu, 02 Jul 2026 02:06:39 GMT
• Title: Beyond the Expressivity-Trainability Paradox: A Dynamical Lie Algebra Perspective on Navigating Barren Plateaus in Quantum Machine Learning
• Abstract summary: In Quantum Machine Learning (QML), increasing model capacity typically risks overfitting.<n>This study advances a counter-intuitive paradigm, driven by the "expressivity-trainability paradox"<n>We establish a comprehensive framework linking the algebraic dimension of circuit generators to their optimization dynamics.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Learnable yet not simulable: a quantum resource theory of learning models [57.695822250391906]
  It remains unclear which quantum resource governs the classical learnability of quantum circuits.<n>We study the expectation-value functions of families of tunable quantum circuits.<n>These results establish a quantitative resource-theoretic framework for delineating the boundary between classical simulation and learning.
  arXiv  Detail & Related papers  (2026-08-03T14:48:03Z)
• Trainable Quantum Channels as Computational Primitives for Quantum Learning [2.047424180164312]
  Variational quantum learning is traditionally constrained to unitary dynamics.<n>We establish a non-unitary quantum machine learning framework grounded in open-system dynamics.
  arXiv  Detail & Related papers  (2026-06-14T13:19:49Z)
• Compositional Quantum Heuristics for Max-Clique Detection [0.0]
  In general, circuits that are sufficiently expressive to model complex behaviour often exhibit barren plateaus.<n>In this work we investigate a compositional approach to mitigate this trade-off by assembling larger quantum models from smaller subcomponents.<n>We use this framework to design permutation-equivariant quantum graph neural networks for identifying maximal cliques in graphs.
  arXiv  Detail & Related papers  (2026-05-08T11:38:57Z)
• Quantum LEGO Learning: A Modular Design Principle for Hybrid Artificial Intelligence [63.39968536637762]
  We introduce Quantum LEGO Learning, a learning framework that treats classical and quantum components as reusable, composable learning blocks.<n>Within this framework, a pre-trained classical neural network serves as a frozen feature block, while a VQC acts as a trainable adaptive module.<n>We develop a block-wise generalization theory that decomposes learning error into approximation and estimation components.
  arXiv  Detail & Related papers  (2026-01-29T14:29:21Z)
• Physics-Informed Hybrid Quantum-Classical Dispatching for Large-Scale Renewable Power Systems:A Noise-Resilient Framework [9.378801906395179]
  High-penetration energy introduces significantity and non-Classicality into power system dispatching optimization.<n>Existing approaches typically treat the power grid as a "black box"<n>This paper proposes a Hybrid Quantum-Bridging Dispatching (PIHQ-CD) framework.
  arXiv  Detail & Related papers  (2026-01-26T13:35:54Z)
• Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing [68.35481158940401]
  CL-QAS is a continual quantum architecture search framework.<n>It mitigates challenges of costly encoding amplitude and forgetting in variational quantum circuits.<n>It achieves controllable robustness expressivity, sample-efficient generalization, and smooth convergence without barren plateaus.
  arXiv  Detail & Related papers  (2026-01-10T02:36:03Z)
• Superpositional Gradient Descent: Harnessing Quantum Principles for Model Training [0.0]
  Superpositional Gradient Descent (SGD) is a novel linking gradient updates with quantum superposition by injecting quantum circuit perturbations.<n>We present a mathematical framework and implement hybrid quantum-classical circuits in PyTorch and Qiskit.
  arXiv  Detail & Related papers  (2025-11-01T16:37:55Z)
• LCQNN: Linear Combination of Quantum Neural Networks [7.010027035873597]
  We introduce the Linear Combination of Quantum Neural Networks (LCQNN) framework, which uses the linear combination of unitaries concept to create a tunable design.<n>We show how specific structural choices, such as adopting $k$ of control unitaries or restricting the model to certain group-theoretic subspaces, prevent gradients from collapsing.<n>In group action scenarios, we show that by exploiting symmetry and excluding exponentially large irreducible subspaces, the model circumvents barren plateaus.
  arXiv  Detail & Related papers  (2025-07-03T17:43:10Z)
• VQC-MLPNet: An Unconventional Hybrid Quantum-Classical Architecture for Scalable and Robust Quantum Machine Learning [50.95799256262098]
  Variational quantum circuits (VQCs) hold promise for quantum machine learning but face challenges in expressivity, trainability, and noise resilience.<n>We propose VQC-MLPNet, a hybrid architecture where a VQC generates the first-layer weights of a classical multilayer perceptron during training, while inference is performed entirely classically.
  arXiv  Detail & Related papers  (2025-06-12T01:38:15Z)
• Leveraging Pre-Trained Neural Networks to Enhance Machine Learning with Variational Quantum Circuits [48.33631905972908]
  We introduce an innovative approach that utilizes pre-trained neural networks to enhance Variational Quantum Circuits (VQC) This technique effectively separates approximation error from qubit count and removes the need for restrictive conditions. Our results extend to applications such as human genome analysis, demonstrating the broad applicability of our approach.
  arXiv  Detail & Related papers  (2024-11-13T12:03:39Z)
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [62.46800898243033]
  Recent progress in quantum learning theory prompts a question: can linear properties of a large-qubit circuit be efficiently learned from measurement data generated by varying classical inputs?<n>We prove that the sample complexity scaling linearly in $d$ is required to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d.<n>We propose a kernel-based method leveraging classical shadows and truncated trigonometric expansions, enabling a controllable trade-off between prediction accuracy and computational overhead.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• Pre-training Tensor-Train Networks Facilitates Machine Learning with Variational Quantum Circuits [70.97518416003358]
  Variational quantum circuits (VQCs) hold promise for quantum machine learning on noisy intermediate-scale quantum (NISQ) devices. While tensor-train networks (TTNs) can enhance VQC representation and generalization, the resulting hybrid model, TTN-VQC, faces optimization challenges due to the Polyak-Lojasiewicz (PL) condition. To mitigate this challenge, we introduce Pre+TTN-VQC, a pre-trained TTN model combined with a VQC.
  arXiv  Detail & Related papers  (2023-05-18T03:08:18Z)
• The Quantum Path Kernel: a Generalized Quantum Neural Tangent Kernel for Deep Quantum Machine Learning [52.77024349608834]
  Building a quantum analog of classical deep neural networks represents a fundamental challenge in quantum computing. Key issue is how to address the inherent non-linearity of classical deep learning. We introduce the Quantum Path Kernel, a formulation of quantum machine learning capable of replicating those aspects of deep machine learning.
  arXiv  Detail & Related papers  (2022-12-22T16:06:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.